To see the other types of publications on this topic, follow the link: Machine and deep learning.
Dissertations / Theses on the topic 'Machine and deep learning'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Machine and deep learning.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Fan, Shuangfei. "Deep Representation Learning on Labeled Graphs." Diss., Virginia Tech, 2020. http://hdl.handle.net/10919/96596.
Full textAbstract:
We introduce recurrent collective classification (RCC), a variant of ICA analogous to recurrent neural network prediction. RCC accommodates any differentiable local classifier and relational feature functions. We provide gradient-based strategies for optimizing over model parameters to more directly minimize the loss function. In our experiments, this direct loss minimization translates to improved accuracy and robustness on real network data. We demonstrate the robustness of RCC in settings where local classification is very noisy, settings that are particularly challenging for ICA. As a new way to train generative models, generative adversarial networks (GANs) have achieved considerable success in image generation, and this framework has also recently been applied to data with graph structures. We identify the drawbacks of existing deep frameworks for generating graphs, and we propose labeled-graph generative adversarial networks (LGGAN) to train deep generative models for graph-structured data with node labels. We test the approach on various types of graph datasets, such as collections of citation networks and protein graphs. Experiment results show that our model can generate diverse labeled graphs that match the structural characteristics of the training data and outperforms all baselines in terms of quality, generality, and scalability. To further evaluate the quality of the generated graphs, we apply it to a downstream task for graph classification, and the results show that LGGAN can better capture the important aspects of the graph structure.Doctor of Philosophy
Graphs are one of the most important and powerful data structures for conveying the complex and correlated information among data points. In this research, we aim to provide more robust and accurate models for some graph specific tasks, such as collective classification and graph generation, by designing deep learning models to learn better task-specific representations for graphs. First, we studied the collective classification problem in graphs and proposed recurrent collective classification, a variant of the iterative classification algorithm that is more robust to situations where predictions are noisy or inaccurate. Then we studied the problem of graph generation using deep generative models. We first proposed a deep generative model using the GAN framework that generates labeled graphs. Then in order to support more applications and also get more control over the generated graphs, we extended the problem of graph generation to conditional graph generation which can then be applied to various applications for modeling graph evolution and transformation.
2
Zhuang, Zhongfang. "Deep Learning on Attributed Sequences." Digital WPI, 2019. https://digitalcommons.wpi.edu/etd-dissertations/507.
Full textAbstract:
Recent research in feature learning has been extended to sequence data, where each instance consists of a sequence of heterogeneous items with a variable length. However, in many real-world applications, the data exists in the form of attributed sequences, which is composed of a set of fixed-size attributes and variable-length sequences with dependencies between them. In the attributed sequence context, feature learning remains challenging due to the dependencies between sequences and their associated attributes. In this dissertation, we focus on analyzing and building deep learning models for four new problems on attributed sequences. First, we propose a framework, called NAS, to produce feature representations of attributed sequences in an unsupervised fashion. The NAS is capable of producing task independent embeddings that can be used in various mining tasks of attributed sequences. Second, we study the problem of deep metric learning on attributed sequences. The goal is to learn a distance metric based on pairwise user feedback. In this task, we propose a framework, called MLAS, to learn a distance metric that measures the similarity and dissimilarity between attributed sequence feedback pairs. Third, we study the problem of one-shot learning on attributed sequences. This problem is important for a variety of real-world applications ranging from fraud prevention to network intrusion detection. We design a deep learning framework OLAS to tackle this problem. Once the OLAS is trained, we can then use it to make predictions for not only the new data but also for entire previously unseen new classes. Lastly, we investigate the problem of attributed sequence classification with attention model. This is challenging that now we need to assess the importance of each item in each sequence considering both the sequence itself and the associated attributes. In this work, we propose a framework, called AMAS, to classify attributed sequences using the information from the sequences, metadata, and the computed attention. Our extensive experiments on real-world datasets demonstrate that the proposed solutions significantly improve the performance of each task over the state-of-the-art methods on attributed sequences.
3
Elmarakeby, Haitham Abdulrahman. "Deep Learning for Biological Problems." Diss., Virginia Tech, 2017. http://hdl.handle.net/10919/86264.
Full textAbstract:
The last decade has witnessed a tremendous increase in the amount of available biological data. Different technologies for measuring the genome, epigenome, transcriptome, proteome, metabolome, and microbiome in different organisms are producing large amounts of high-dimensional data every day. High-dimensional data provides unprecedented challenges and opportunities to gain a better understanding of biological systems. Unlike other data types, biological data imposes more constraints on researchers. Biologists are not only interested in accurate predictive models that capture complex input-output relationships, but they also seek a deep understanding of these models.
In the last few years, deep models have achieved better performance in computational prediction tasks compared to other approaches. Deep models have been extensively used in processing natural data, such as images, text, and recently sound. However, application of deep models in biology is limited. Here, I propose to use deep models for output prediction, dimension reduction, and feature selection of biological data to get better interpretation and understanding of biological systems. I demonstrate the applicability of deep models in a domain that has a high and direct impact on health care.
In this research, novel deep learning models have been introduced to solve pressing biological problems. The research shows that deep models can be used to automatically extract features from raw inputs without the need to manually craft features. Deep models are used to reduce the dimensionality of the input space, which resulted in faster training. Deep models are shown to have better performance and less variant output when compared to other shallow models even when an ensemble of shallow models is used. Deep models are shown to be able to process non-classical inputs such as sequences. Deep models are shown to be able to naturally process input sequences to automatically extract useful features.Ph. D.
4
Arnold, Ludovic. "Learning Deep Representations : Toward a better new understanding of the deep learning paradigm." Phd thesis, Université Paris Sud - Paris XI, 2013. http://tel.archives-ouvertes.fr/tel-00842447.
Full textAbstract:
Since 2006, deep learning algorithms which rely on deep architectures with several layers of increasingly complex representations have been able to outperform state-of-the-art methods in several settings. Deep architectures can be very efficient in terms of the number of parameters required to represent complex operations which makes them very appealing to achieve good generalization with small amounts of data. Although training deep architectures has traditionally been considered a difficult problem, a successful approach has been to employ an unsupervised layer-wise pre-training step to initialize deep supervised models. First, unsupervised learning has many benefits w.r.t. generalization because it only relies on unlabeled data which is easily found. Second, the possibility to learn representations layer by layer instead of all layers at once improves generalization further and reduces computational time. However, deep learning is a very recent approach and still poses a lot of theoretical and practical questions concerning the consistency of layer-wise learning with many layers and difficulties such as evaluating performance, performing model selection and optimizing layers. In this thesis we first discuss the limitations of the current variational justification for layer-wise learning which does not generalize well to many layers. We ask if a layer-wise method can ever be truly consistent, i.e. capable of finding an optimal deep model by training one layer at a time without knowledge of the upper layers. We find that layer-wise learning can in fact be consistent and can lead to optimal deep generative models. To do this, we introduce the Best Latent Marginal (BLM) upper bound, a new criterion which represents the maximum log-likelihood of a deep generative model where the upper layers are unspecified. We prove that maximizing this criterion for each layer leads to an optimal deep architecture, provided the rest of the training goes well. Although this criterion cannot be computed exactly, we show that it can be maximized effectively by auto-encoders when the encoder part of the model is allowed to be as rich as possible. This gives a new justification for stacking models trained to reproduce their input and yields better results than the state-of-the-art variational approach. Additionally, we give a tractable approximation of the BLM upper-bound and show that it can accurately estimate the final log-likelihood of models. Taking advantage of these theoretical advances, we propose a new method for performing layer-wise model selection in deep architectures, and a new criterion to assess whether adding more layers is warranted. As for the difficulty of training layers, we also study the impact of metrics and parametrization on the commonly used gradient descent procedure for log-likelihood maximization. We show that gradient descent is implicitly linked with the metric of the underlying space and that the Euclidean metric may often be an unsuitable choice as it introduces a dependence on parametrization and can lead to a breach of symmetry. To mitigate this problem, we study the benefits of the natural gradient and show that it can restore symmetry, regrettably at a high computational cost. We thus propose that a centered parametrization may alleviate the problem with almost no computational overhead.
5
Tegendal, Lukas. "Watermarking in Audio using Deep Learning." Thesis, Linköpings universitet, Datorseende, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-159191.
Full textAbstract:
Watermarking is a technique used to used to mark the ownership in media such as audio or images by embedding a watermark, e.g. copyrights information, into the media. A good watermarking method should perform this embedding without affecting the quality of the media. Recent methods for watermarking in images uses deep learning to embed and extract the watermark in the images. In this thesis, we investigate watermarking in the hearable frequencies of audio using deep learning. More specifically, we try to create a watermarking method for audio that is robust to noise in the carrier, and that allows for the extraction of the embedded watermark from the audio after being played over-the-air. The proposed method consists of two deep convolutional neural network trained end-to-end on music with simulated noise. Experiments show that the proposed method successfully creates watermarks robust to simulated noise with moderate quality reductions, but it is not robust to the real world noise introduced after playing and recording the audio over-the-air.
6
Shi, Shaohuai. "Communication optimizations for distributed deep learning." HKBU Institutional Repository, 2020. https://repository.hkbu.edu.hk/etd_oa/813.
Full textAbstract:
With the increasing amount of data and the growing computing power, deep learning techniques using deep neural networks (DNNs) have been successfully applied in many practical artificial intelligence applications. The mini-batch stochastic gradient descent (SGD) algorithm and its variants are the most widely used algorithms in training deep models. The SGD algorithm is an iterative algorithm that needs to update the model parameters many times by traversing the training data, which is very time-consuming even using the single powerful GPU or TPU. Therefore, it becomes a common practice to exploit multiple processors (e.g., GPUs or TPUs) to accelerate the training process using distributed SGD. However, the iterative nature of distributed SGD requires multiple processors to iteratively communicate with each other to collaboratively update the model parameters. The intensive communication cost easily becomes the system bottleneck and limits the system scalability. In this thesis, we study the communication-efficient techniques for distributed SGD to improve the system scalability and thus accelerate the training process. We identify the performance issues in distributed SGD through benchmarking and modeling and then propose several communication optimization algorithms to address the communication issues. First, we build a performance model with a directed acyclic graph (DAG) to modeling the training process of distributed SGD and verify the model with extensive benchmarks on existing state-of-the-art deep learning frameworks including Caffe, MXNet, TensorFlow, and CNTK. Our benchmarking and modeling point out that existing optimizations for the communication problems are sub-optimal, which we need to address in this thesis. Second, to address the startup problem (due to the high latency of each communication) of layer-wise communications with wait-free backpropagation (WFBP), we propose an optimal gradient merging solution for WFBP, named MG-WFBP, that exploits the layer-wise property to well overlap the communication tasks with the computing tasks and can be adaptive to the training environments. Experiments are conducted on dense-GPU clusters with Ethernet and InfiniBand, and the results show that MG-WFBP can well address the startup problem in distributed training of layer-wise structured DNNs. Third, to make the high computing-intensive training tasks be possible in GPU clusters with low- bandwidth interconnect, we investigate the gradient compression techniques in distributed training. The top-{dollar}k{dollar} sparsification can well compress the communication traffic with little impact on the model convergence, but it suffers from a linear communication complexity to the number of workers so that top-{dollar}k{dollar} sparsification cannot scale well in large-scale clusters. To address the problem, we propose a global top-{dollar}k{dollar} (gTop-{dollar}k{dollar}) sparsification algorithm that reduces the communication complexity to be logarithmic to the number of workers. We also provide detailed theoretical analysis for the gTop-{dollar}k{dollar} SGD training algorithm, and the theoretical results show that our gTop-{dollar}k{dollar} SGD has the same order of convergence rate with SGD. Experiments are conducted on up to 64-GPU cluster to verify that gTop-{dollar}k{dollar} SGD significantly improves the system scalability with only a slight impact on the model convergence. Lastly, to enjoy the both benefits of the pipelining technique and the gradient sparsification algorithm, we propose a new distributed training algorithm, layer-wise adaptive gradient sparsification SGD (LAGS-SGD), which supports layer-wise sparsification and communication, and we theoretically and empirically prove that the LAGS-SGD preserves the convergence properties. To further alliterate the impact of the startup problem of layer-wise communications in LAGS-SGD, we also propose the optimal gradient merging solution for LAGS-SGD, named OMGS-SGD, and theoretical prove its optimality. The experimental results on a 16-node GPU cluster connected 1Gbps Ethernet show that OMGS-SGD can always improve the system scalability while the model convergence properties are not affected
7
Manda, Kundan Reddy. "Sentiment Analysis of Twitter Data Using Machine Learning and Deep Learning Methods." Thesis, Blekinge Tekniska Högskola, Institutionen för datavetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18447.
Full textAbstract:
Background: Twitter, Facebook, WordPress, etc. act as the major sources of information exchange in today's world. The tweets on Twitter are mainly based on the public opinion on a product, event or topic and thus contains large volumes of unprocessed data. Synthesis and Analysis of this data is very important and difficult due to the size of the dataset. Sentiment analysis is chosen as the apt method to analyse this data as this method does not go through all the tweets but rather relates to the sentiments of these tweets in terms of positive, negative and neutral opinions. Sentiment Analysis is normally performed in 3 ways namely Machine learning-based approach, Sentiment lexicon-based approach, and Hybrid approach. The Machine learning based approach uses machine learning algorithms and deep learning algorithms for analysing the data, whereas the sentiment lexicon-based approach uses lexicons in analysing the data and they contain vocabulary of positive and negative words. The Hybrid approach uses a combination of both Machine learning and sentiment lexicon approach for classification. Objectives: The primary objectives of this research are: To identify the algorithms and metrics for evaluating the performance of Machine Learning Classifiers. To compare the metrics from the identified algorithms depending on the size of the dataset that affects the performance of the best-suited algorithm for sentiment analysis. Method: The method chosen to address the research questions is Experiment. Through which the identified algorithms are evaluated with the selected metrics. Results: The identified machine learning algorithms are Naïve Bayes, Random Forest, XGBoost and the deep learning algorithm is CNN-LSTM. The algorithms are evaluated with respect to the metrics namely precision, accuracy, F1 score, recall and compared. CNN-LSTM model is best suited for sentiment analysis on twitter data with respect to the selected size of the dataset. Conclusion: Through the analysis of results, the aim of this research is achieved in identifying the best-suited algorithm for sentiment analysis on twitter data with respect to the selected dataset. CNN-LSTM model results in having the highest accuracy of 88% among the selected algorithms for the sentiment analysis of Twitter data with respect to the selected dataset.
8
Flowers, Bryse Austin. "Adversarial RFML: Evading Deep Learning Enabled Signal Classification." Thesis, Virginia Tech, 2019. http://hdl.handle.net/10919/91987.
Full textAbstract:
Deep learning has become an ubiquitous part of research in all fields, including wireless communications. Researchers have shown the ability to leverage deep neural networks (DNNs) that operate on raw in-phase and quadrature samples, termed Radio Frequency Machine Learning (RFML), to synthesize new waveforms, control radio resources, as well as detect and classify signals. While there are numerous advantages to RFML, this thesis answers the question "is it secure?" DNNs have been shown, in other applications such as Computer Vision (CV), to be vulnerable to what are known as adversarial evasion attacks, which consist of corrupting an underlying example with a small, intelligently crafted, perturbation that causes a DNN to misclassify the example. This thesis develops the first threat model that encompasses the unique adversarial goals and capabilities that are present in RFML. Attacks that occur with direct digital access to the RFML classifier are differentiated from physical attacks that must propagate over-the-air (OTA) and are thus subject to impairments due to the wireless channel or inaccuracies in the signal detection stage. This thesis first finds that RFML systems are vulnerable to current adversarial evasion attacks using the well known Fast Gradient Sign Method originally developed for CV applications. However, these current adversarial evasion attacks do not account for the underlying communications and therefore the adversarial advantage is limited because the signal quickly becomes unintelligible. In order to envision new threats, this thesis goes on to develop a new adversarial evasion attack that takes into account the underlying communications and wireless channel models in order to create adversarial evasion attacks with more intelligible underlying communications that generalize to OTA attacks.Master of Science
Deep learning is beginning to permeate many commercial products and is being included in prototypes for next generation wireless communications devices. This technology can provide huge breakthroughs in autonomy; however, it is not sufficient to study the effectiveness of deep learning in an idealized laboratory environment, the real world is often harsh and/or adversarial. Therefore, it is important to know how, and when, these deep learning enabled devices will fail in the presence of bad actors before they are deployed in high risk environments, such as battlefields or connected autonomous vehicle communications. This thesis studies a small subset of the security vulnerabilities of deep learning enabled wireless communications devices by attempting to evade deep learning enabled signal classification by an eavesdropper while maintaining effective wireless communications with a cooperative receiver. The primary goal of this thesis is to define the threats to, and identify the current vulnerabilities of, deep learning enabled signal classification systems, because a system can only be secured once its vulnerabilities are known.
9
Franch, Gabriele. "Deep Learning for Spatiotemporal Nowcasting." Doctoral thesis, Università degli studi di Trento, 2021. http://hdl.handle.net/11572/295096.
Full textAbstract:
Nowcasting – short-term forecasting using current observations – is a key challenge that human activities have to face on a daily basis. We heavily rely on short-term meteorological predictions in domains such as aviation, agriculture, mobility, and energy production. One of the most important and challenging task for meteorology is the nowcasting of extreme events, whose anticipation is highly needed to mitigate risk in terms of social or economic costs and human safety. The goal of this thesis is to contribute with new machine learning methods to improve the spatio-temporal precision of nowcasting of extreme precipitation events. This work relies on recent advances in deep learning for nowcasting, adding methods targeted at improving nowcasting using ensembles and trained on novel original data resources. Indeed, the new curated multi-year radar scan dataset (TAASRAD19) is introduced that contains more than 350.000 labelled precipitation records over 10 years, to provide a baseline benchmark, and foster reproducibility of machine learning modeling. A TrajGRU model is applied to TAASRAD19, and implemented in an operational prototype. The thesis also introduces a novel method for fast analog search based on manifold learning: the tool leverages the entire dataset history in less than 5 seconds and demonstrates the feasibility of predictive ensembles. In the final part of the thesis, the new deep learning architecture ConvSG based on stacked generalization is presented, introducing novel concepts for deep learning in precipitation nowcasting: ConvSG is specifically designed to improve predictions of extreme precipitation regimes over published methods, and shows a 117% skill improvement on extreme rain regimes over a single member. Moreover, ConvSG shows superior or equal skills compared to Lagrangian Extrapolation models for all rain rates, achieving a 49% average improvement in predictive skill over extrapolation on the higher precipitation regimes.
10
Rigaki, Maria. "Adversarial Deep Learning Against Intrusion Detection Classifiers." Thesis, Luleå tekniska universitet, Datavetenskap, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:ltu:diva-64577.
Full textAbstract:
Traditional approaches in network intrusion detection follow a signature-based ap- proach, however the use of anomaly detection approaches based on machine learning techniques have been studied heavily for the past twenty years. The continuous change in the way attacks are appearing, the volume of attacks, as well as the improvements in the big data analytics space, make machine learning approaches more alluring than ever. The intention of this thesis is to show that using machine learning in the intrusion detection domain should be accompanied with an evaluation of its robustness against adversaries. Several adversarial techniques have emerged lately from the deep learning research, largely in the area of image classification. These techniques are based on the idea of introducing small changes in the original input data in order to make a machine learning model to misclassify it. This thesis follows a big data Analytics methodol- ogy and explores adversarial machine learning techniques that have emerged from the deep learning domain, against machine learning classifiers used for network intrusion detection. The study looks at several well known classifiers and studies their performance under attack over several metrics, such as accuracy, F1-score and receiver operating character- istic. The approach used assumes no knowledge of the original classifier and examines both general and targeted misclassification. The results show that using relatively sim- ple methods for generating adversarial samples it is possible to lower the detection accuracy of intrusion detection classifiers from 5% to 28%. Performance degradation is achieved using a methodology that is simpler than previous approaches and it re- quires only 6.25% change between the original and the adversarial sample, making it a candidate for a practical adversarial approach.
11
Mariani, Tommaso. "Deep reinforcement learning for industrial applications." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20548/.
Full textAbstract:
In recent years there has been a growing attention from the world of research and companies in the field of Machine Learning. This interest, thanks mainly to the increasing availability of large amounts of data, and the respective strengthening of the hardware sector useful for their analysis, has led to the birth of Deep Learning. The growing computing capacity and the use of mathematical optimization techniques, already studied in depth but with few applications due to a low computational power, have then allowed the development of a new approach called Reinforcement Learning.
This thesis work is part of an industrial process of selection of fruit for sale, thanks to the identification and classification of any defects present on it. The final objective is to measure the similarity between them, being able to identify and link them together, even if coming from optical acquisitions obtained at different time steps.
We therefore studied a class of algorithms characteristic of Reinforcement Learning, the policy gradient methods, in order to train a feedforward neural network to compare possible malformations of the same fruit. Finally, an applicability study was made, based on real data, in which the model was compared on different fruit rolling dynamics and with different versions of the network.
12
Ida, Yasutoshi. "Algorithms for Accelerating Machine Learning with Wide and Deep Models." Doctoral thesis, Kyoto University, 2021. http://hdl.handle.net/2433/263771.
Full text
13
Kostopouls, Theodore P. "A Machine Learning approach to Febrile Classification." Digital WPI, 2018. https://digitalcommons.wpi.edu/etd-theses/1173.
Full textAbstract:
General health screening is needed to decrease the risk of pandemic in high volume areas. Thermal characterization, via infrared imaging, is an effective technique for fever detection, however, strict use requirements in combination with highly controlled environmental conditions compromise the practicality of such a system. Combining advanced processing techniques to thermograms of individuals can remove some of these requirements allowing for more flexible classification algorithms. The purpose of this research was to identify individuals who had febrile status utilizing modern thermal imaging and machine learning techniques in a minimally controlled setting. Two methods were evaluated with data that contained environmental, and acclimation noise due to data gathering technique. The first was a pretrained VGG16 Convolutional Neural Network found to have F1 score of 0.77 (accuracy of 76%) on a balanced dataset. The second was a VGG16 Feature Extractor that gives inputs to a principle components analysis and utilizes a support vector machine for classification. This technique obtained a F1 score of 0.84 (accuracy of 85%) on balanced data sets. These results demonstrate that machine learning is an extremely viable technique to classify febrile status independent of noise affiliated.
14
Shao, Han. "Pretraining Deep Learning Models for Natural Language Understanding." Oberlin College Honors Theses / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=oberlin158955297757398.
Full text
15
Darborg, Alex. "Real-time face recognition using one-shot learning : A deep learning and machine learning project." Thesis, Mittuniversitetet, Institutionen för informationssystem och –teknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-40069.
Full textAbstract:
Face recognition is often described as the process of identifying and verifying people in a photograph by their face. Researchers have recently given this field increased attention, continuously improving the underlying models. The objective of this study is to implement a real-time face recognition system using one-shot learning. “One shot” means learning from one or few training samples. This paper evaluates different methods to solve this problem. Convolutional neural networks are known to require large datasets to reach an acceptable accuracy. This project proposes a method to solve this problem by reducing the number of training instances to one and still achieving an accuracy close to 100%, utilizing the concept of transfer learning.
16
Geras, Krzysztof Jerzy. "Exploiting diversity for efficient machine learning." Thesis, University of Edinburgh, 2018. http://hdl.handle.net/1842/28839.
Full textAbstract:
A common practice for solving machine learning problems is currently to consider each problem in isolation, starting from scratch every time a new learning problem is encountered or a new model is proposed. This is a perfectly feasible solution when the problems are sufficiently easy or, if the problem is hard when a large amount of resources, both in terms of the training data and computation, are available. Although this naive approach has been the main focus of research in machine learning for a few decades and had a lot of success, it becomes infeasible if the problem is too hard in proportion to the available resources. When using a complex model in this naive approach, it is necessary to collect large data sets (if possible at all) to avoid overfitting and hence it is also necessary to use large computational resources to handle the increased amount of data, first during training to process a large data set and then also at test time to execute a complex model. An alternative to this strategy of treating each learning problem independently is to leverage related data sets and computation encapsulated in previously trained models. By doing that we can decrease the amount of data necessary to reach a satisfactory level of performance and, consequently, improve the accuracy achievable and decrease training time. Our attack on this problem is to exploit diversity - in the structure of the data set, in the features learnt and in the inductive biases of different neural network architectures. In the setting of learning from multiple sources we introduce multiple-source cross-validation, which gives an unbiased estimator of the test error when the data set is composed of data coming from multiple sources and the data at test time are coming from a new unseen source. We also propose new estimators of variance of the standard k-fold cross-validation and multiple-source cross-validation, which have lower bias than previously known ones. To improve unsupervised learning we introduce scheduled denoising autoencoders, which learn a more diverse set of features than the standard denoising auto-encoder. This is thanks to their training procedure, which starts with a high level of noise, when the network is learning coarse features and then the noise is lowered gradually, which allows the network to learn some more local features. A connection between this training procedure and curriculum learning is also drawn. We develop further the idea of learning a diverse representation by explicitly incorporating the goal of obtaining a diverse representation into the training objective. The proposed model, the composite denoising autoencoder, learns multiple subsets of features focused on modelling variations in the data set at different levels of granularity. Finally, we introduce the idea of model blending, a variant of model compression, in which the two models, the teacher and the student, are both strong models, but different in their inductive biases. As an example, we train convolutional networks using the guidance of bidirectional long short-term memory (LSTM) networks. This allows to train the convolutional neural network to be more accurate than the LSTM network at no extra cost at test time.
17
Zhao, Yajing. "Chaotic Model Prediction with Machine Learning." BYU ScholarsArchive, 2020. https://scholarsarchive.byu.edu/etd/8419.
Full textAbstract:
Chaos theory is a branch of modern mathematics concerning the non-linear dynamic systems that are highly sensitive to their initial states. It has extensive real-world applications, such as weather forecasting and stock market prediction. The Lorenz system, defined by three ordinary differential equations (ODEs), is one of the simplest and most popular chaotic models. Historically research has focused on understanding the Lorenz system's mathematical characteristics and dynamical evolution including the inherent chaotic features it possesses. In this thesis, we take a data-driven approach and propose the task of predicting future states of the chaotic system from limited observations. We explore two directions, answering two distinct fundamental questions of the system based on how informed we are about the underlying model. When we know the data is generated by the Lorenz System with unknown parameters, our task becomes parameter estimation (a white-box problem), or the ``inverse'' problem. When we know nothing about the underlying model (a black-box problem), our task becomes sequence prediction. We propose two algorithms for the white-box problem: Markov-Chain-Monte-Carlo (MCMC) and a Multi-Layer-Perceptron (MLP). Specially, we propose to use the Metropolis-Hastings (MH) algorithm with an additional random walk to avoid the sampler being trapped into local energy wells. The MH algorithm achieves moderate success in predicting the $\rho$ value from the data, but fails at the other two parameters. Our simple MLP model is able to attain high accuracy in terms of the $l_2$ distance between the prediction and ground truth for $\rho$ as well, but also fails to converge satisfactorily for the remaining parameters. We use a Recurrent Neural Network (RNN) to tackle the black-box problem. We implement and experiment with several RNN architectures including Elman RNN, LSTM, and GRU and demonstrate the relative strengths and weaknesses of each of these methods. Our results demonstrate the promising role of machine learning and modern statistical data science methods in the study of chaotic dynamic systems. The code for all of our experiments can be found on \url{https://github.com/Yajing-Zhao/}
18
Jaderberg, Maxwell. "Deep learning for text spotting." Thesis, University of Oxford, 2015. http://ora.ox.ac.uk/objects/uuid:e893c11e-6b6b-4d11-bb25-846bcef9b13e.
Full textAbstract:
This thesis addresses the problem of text spotting - being able to automatically detect and recognise text in natural images. Developing text spotting systems, systems capable of reading and therefore better interpreting the visual world, is a challenging but wildly useful task to solve. We approach this problem by drawing on the successful developments in machine learning, in particular deep learning and neural networks, to present advancements using these data-driven methods. Deep learning based models, consisting of millions of trainable parameters, require a lot of data to train effectively. To meet the requirements of these data hungry algorithms, we present two methods of automatically generating extra training data without any additional human interaction. The first crawls a photo sharing website and uses a weakly-supervised existing text spotting system to harvest new data. The second is a synthetic data generation engine, capable of generating unlimited amounts of realistic looking text images, that can be solely relied upon for training text recognition models. While we define these new datasets, all our methods are also evaluated on standard public benchmark datasets. We develop two approaches to text spotting: character-centric and word-centric. In the character-centric approach, multiple character classifier models are developed, reinforcing each other through a feature sharing framework. These character models are used to generate text saliency maps to drive detection, and convolved with detection regions to enable text recognition, producing an end-to-end system with state-of-the-art performance. For the second, higher-level, word-centric approach to text spotting, weak detection models are constructed to find potential instances of words in images, which are subsequently refined and adjusted with a classifier and deep coordinate regressor. A whole word image recognition model recognises words from a huge dictionary of 90k words using classification, resulting in previously unattainable levels of accuracy. The resulting end-to-end text spotting pipeline advances the state of the art significantly and is applied to large scale video search. While dictionary based text recognition is useful and powerful, the need for unconstrained text recognition still prevails. We develop a two-part model for text recognition, with the complementary parts combined in a graphical model and trained using a structured output learning framework adapted to deep learning. The trained recognition model is capable of accurately recognising unseen and completely random text. Finally, we make a general contribution to improve the efficiency of convolutional neural networks. Our low-rank approximation schemes can be utilised to greatly reduce the number of computations required for inference. These are applied to various existing models, resulting in real-world speedups with negligible loss in predictive power.
19
Al, Chalati Abdul Aziz, and Syed Asad Naveed. "Transfer Learning for Machine Diagnostics." Thesis, Högskolan i Halmstad, Akademin för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-43185.
Full textAbstract:
Fault detection and diagnostics are crucial tasks in condition-based maintenance. Industries nowadays are in need of fault identification in their machines as early as possible to save money and take precautionary measures in case of fault occurrence. Also, it is beneficial for the smooth interference in the manufacturing process in which it avoids sudden malfunctioning. Having sufficient training data for industrial machines is also a major challenge which is a prerequisite for deep neural networks to train an accurate prediction model. Transfer learning in such cases is beneficial as it can be helpful in adapting different operating conditions and characteristics which is the casein real-life applications. Our work is focused on a pneumatic system which utilizes compressed air to perform operations and is used in different types of machines in the industrial field. Our novel contribution is to build upon a Domain Adversarial Neural Network (DANN) with a unique approach by incorporating ensembling techniques for diagnostics of air leakage problem in the pneumatic system under transfer learning settings. Our approach of using ensemble methods for feature extraction shows up to 5 % improvement in the performance. We have also performed a comparative analysis of our work with conventional machine and deep learning methods which depicts the importance of transfer learning and we have also demonstrated the generalization ability of our model. Lastly, we also mentioned a problem specific contribution by suggesting a feature engineering approach, such that it could be implemented on almost every pneumatic system and could potentially impact the prediction result positively. We demonstrate that our designed model with domain adaptation ability will be quite useful and beneficial for the industry by saving their time and money and providing promising results for this air leakage problem in the pneumatic system.
20
Morri, Francesco. "A thermodynamic approach to deep learning." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020.
Find full textAbstract:
Neural Networks are an incredibly powerful tool used to solve complex problems.
The actual functioning of this tool and its behaviour when applied to different kind of problems is not completely explain though.
In this work we study the behaviour of a neural network, used to classify images, through a physical model, based on statistical thermodynamics. We found interesting results regarding the temperature of the different components of the network, that may be exploited in a more efficient training algorithm.
21
Emenonye, Don-Roberts Ugochukwu. "Application of Machine Learning to Multi Antenna Transmission and Machine Type Resource Allocation." Thesis, Virginia Tech, 2020. http://hdl.handle.net/10919/99956.
Full textAbstract:
Wireless communication systems is a well-researched area in electrical engineering that
has continually evolved over the past decades. This constant evolution and development
have led to well-formulated theoretical baselines in terms of reliability and efficiency. However,
most communication baselines are derived by splitting the baseband communications
into a series of modular blocks like modulation, coding, channel estimation, and orthogonal
frequency modulation. Subsequently, these blocks are independently optimized. Although
this has led to a very efficient and reliable process, a theoretical verification of the optimality
of this design process is not feasible due to the complexities of each individual block. In this
work, we propose two modifications to these conventional wireless systems.
First, with the goal of designing better space-time block codes for improved reliability, we
propose to redesign the transmit and receive blocks of the physical layer. We replace a portion
of the transmit chain - from modulation to antenna mapping with a neural network.
Similarly, the receiver/decoder is also replaced with a neural network. In other words, the
first part of this work focuses on jointly optimizing the transmit and receive blocks to produce
a set of space-time codes that are resilient to Rayleigh fading channels. We compare
our results to the conventional orthogonal space-time block codes for multiple antenna configurations.
The second part of this work investigates the possibility of designing a distributed multiagent
reinforcement learning-based multi-access algorithm for machine type communication.
This work recognizes that cellular networks are being proposed as a solution for the connectivity
of machine type devices (MTDs) and one of the most crucial aspects of scheduling in cellular connectivity is the random access procedure. The random access process is used by
conventional cellular users to receive an allocation for the uplink transmissions. This process
usually requires six resource blocks. It is efficient for cellular users to perform this process
because transmission of cellular data usually requires more than six resource blocks. Hence,
it is relatively efficient to perform the random access process in order to establish a connection.
Moreover, as long as cellular users maintain synchronization, they do not have to
undertake the random access process every time they have data to transmit. They can maintain
a connection with the base station through discontinuous reception. On the other hand,
the random access process is unsuitable for MTDs because MTDs usually have small-sized
packets. Hence, performing the random access process to transmit such small-sized packets
is highly inefficient. Also, most MTDs are power constrained, thus they turn off when they
have no data to transmit. This means that they lose their connection and can't maintain
any form of discontinuous reception. Hence, they perform the random process each time
they have data to transmit. Due to these observations, explicit scheduling is undesirable for
MTC.
To overcome these challenges, we propose bypassing the entire scheduling process by using
a grant free resource allocation scheme. In this scheme, MTDs pseudo-randomly transmit
their data in random access slots. Note that this results in the possibility of a large number
of collisions during the random access slots. To alleviate the resulting congestion, we exploit
a heterogeneous network and investigate the optimal MTD-BS association which minimizes
the long term congestion experienced in the overall cellular network. Our results show that
we can derive the optimal MTD-BS association when the number of MTDs is less than the
total number of random access slots.Master of Science
Wireless communication systems is a well researched area of engineering that has continually evolved over the past decades. This constant evolution and development has led to well formulated theoretical baselines in terms of reliability and efficiency. This two part thesis investigates the possibility of improving these wireless systems with machine learning. First, with the goal of designing more resilient codes for transmission, we propose to redesign the transmit and receive blocks of the physical layer. We focus on jointly optimizing the transmit and receive blocks to produce a set of transmit codes that are resilient to channel impairments. We compare our results to the current conventional codes for various transmit and receive antenna configuration. The second part of this work investigates the possibility of designing a distributed multi-access scheme for machine type devices. In this scheme, MTDs pseudo-randomly transmit their data by randomly selecting time slots. This results in the possibility of a large number of collisions occurring in the duration of these slots. To alleviate the resulting congestion, we employ a heterogeneous network and investigate the optimal MTD-BS association which minimizes the long term congestion experienced in the overall network. Our results show that we can derive the optimal MTD-BS algorithm when the number of MTDs is less than the total number of slots.
22
Addis, Antonio. "Deep reinforcement learning optimization of video streaming." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019.
Find full textAbstract:
Questa tesi si occuperà dell'ottimizzazione delle performance di streaming video attraverso internet, divenute particolarmente problematiche con l'avvento delle nuove risoluzioni ultraHD e i video a 360 gradi per la realtà virtuale. Verranno confrontate le performance ottenute con gli algoritmi che attualmente fanno parte dello stato dell'arte, e sviluppato un modello di reinforcement learning che sia capace di effettuare scelte per migliorare la QoE(quality of experience) durante una sessione di streaming.
Per i video a 360 gradi, verrà inoltre implementata la tecnica snapchange, con questo metodo è possibile ridurre la banda utilizzata durante lo streaming, forzando la riposizione dello sguardo dell'utente in un'area di maggior interesse del video.
23
Mansanet, Sandín Jorge. "Contributions to Deep Learning Models." Doctoral thesis, Universitat Politècnica de València, 2016. http://hdl.handle.net/10251/61296.
Full textAbstract:
[EN] Deep Learning is a new area of Machine Learning research which aims to create computational models that learn several representations of the data using deep architectures. These methods have become very popular over the last few years due to the remarkable results obtained in speech recognition, visual object recognition, object detection, natural language processing, etc.
The goal of this thesis is to present some contributions to the Deep Learning framework, particularly focused on computer vision problems dealing with images. These contributions can be summarized in two novel methods proposed: a new regularization technique for Restricted Boltzmann Machines called Mask Selective Regularization (MSR), and a powerful discriminative network called Local Deep Neural Network (Local-DNN).
On the one hand, the MSR method is based on taking advantage of the benefits of the L2 and the L1 regularizations techniques. Both regularizations are applied dynamically on the parameters of the RBM according to the state of the model during training and the topology of the input space.
On the other hand, the Local-DNN model is based on two key concepts: local features and deep architectures. Similar to the convolutional networks, the Local-DNN model learns from local regions in the input image using a deep neural network. The network aims to classify each local feature according to the label of the sample to which it belongs, and all of these local contributions are taken into account during testing using a simple voting scheme.
The methods proposed throughout the thesis have been evaluated in several experiments using various image datasets. The results obtained show the great performance of these approaches, particularly on gender recognition using face images, where the Local-DNN improves other state-of-the-art results.[ES] El Aprendizaje Profundo (Deep Learning en inglés) es una nueva área dentro del campo del Aprendizaje Automático que pretende crear modelos computacionales que aprendan varias representaciones de los datos utilizando arquitecturas profundas. Este tipo de métodos ha ganado mucha popularidad durante los últimos años debido a los impresionantes resultados obtenidos en diferentes tareas como el reconocimiento automático del habla, el reconocimiento y la detección automática de objetos, el procesamiento de lenguajes naturales, etc. El principal objetivo de esta tesis es aportar una serie de contribuciones realizadas dentro del marco del Aprendizaje Profundo, particularmente enfocadas a problemas relacionados con la visión por computador. Estas contribuciones se resumen en dos novedosos métodos: una nueva técnica de regularización para Restricted Boltzmann Machines llamada Mask Selective Regularization (MSR), y una potente red neuronal discriminativa llamada Local Deep Neural Network (Local-DNN). Por una lado, el método MSR se basa en aprovechar las ventajas de las técnicas de regularización clásicas basadas en las normas L2 y L1. Ambas regularizaciones se aplican sobre los parámetros de la RBM teniendo en cuenta el estado del modelo durante el entrenamiento y la topología de los datos de entrada. Por otro lado, El modelo Local-DNN se basa en dos conceptos fundamentales: características locales y arquitecturas profundas. De forma similar a las redes convolucionales, Local-DNN restringe el aprendizaje a regiones locales de la imagen de entrada. La red neuronal pretende clasificar cada característica local con la etiqueta de la imagen a la que pertenece, y, finalmente, todas estas contribuciones se tienen en cuenta utilizando un sencillo sistema de votación durante la predicción. Los métodos propuestos a lo largo de la tesis han sido ampliamente evaluados en varios experimentos utilizando distintas bases de datos, principalmente en problemas de visión por computador. Los resultados obtenidos muestran el buen funcionamiento de dichos métodos, y sirven para validar las estrategias planteadas. Entre ellos, destacan los resultados obtenidos aplicando el modelo Local-DNN al problema del reconocimiento de género utilizando imágenes faciales, donde se han mejorado los resultados publicados del estado del arte.
[CAT] L'Aprenentatge Profund (Deep Learning en anglès) és una nova àrea dins el camp de l'Aprenentatge Automàtic que pretén crear models computacionals que aprenguen diverses representacions de les dades utilitzant arquitectures profundes. Aquest tipus de mètodes ha guanyat molta popularitat durant els últims anys a causa dels impressionants resultats obtinguts en diverses tasques com el reconeixement automàtic de la parla, el reconeixement i la detecció automàtica d'objectes, el processament de llenguatges naturals, etc. El principal objectiu d'aquesta tesi és aportar una sèrie de contribucions realitzades dins del marc de l'Aprenentatge Profund, particularment enfocades a problemes relacionats amb la visió per computador. Aquestes contribucions es resumeixen en dos nous mètodes: una nova tècnica de regularització per Restricted Boltzmann Machines anomenada Mask Selective Regularization (MSR), i una potent xarxa neuronal discriminativa anomenada Local Deep Neural Network ( Local-DNN). D'una banda, el mètode MSR es basa en aprofitar els avantatges de les tècniques de regularització clàssiques basades en les normes L2 i L1. Les dues regularitzacions s'apliquen sobre els paràmetres de la RBM tenint en compte l'estat del model durant l'entrenament i la topologia de les dades d'entrada. D'altra banda, el model Local-DNN es basa en dos conceptes fonamentals: característiques locals i arquitectures profundes. De forma similar a les xarxes convolucionals, Local-DNN restringeix l'aprenentatge a regions locals de la imatge d'entrada. La xarxa neuronal pretén classificar cada característica local amb l'etiqueta de la imatge a la qual pertany, i, finalment, totes aquestes contribucions es fusionen durant la predicció utilitzant un senzill sistema de votació. Els mètodes proposats al llarg de la tesi han estat àmpliament avaluats en diversos experiments utilitzant diferents bases de dades, principalment en problemes de visió per computador. Els resultats obtinguts mostren el bon funcionament d'aquests mètodes, i serveixen per validar les estratègies plantejades. Entre d'ells, destaquen els resultats obtinguts aplicant el model Local-DNN al problema del reconeixement de gènere utilitzant imatges facials, on s'han millorat els resultats publicats de l'estat de l'art.
Mansanet Sandín, J. (2016). Contributions to Deep Learning Models [Tesis doctoral no publicada]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/61296
TESIS
24
Kendall, Alex Guy. "Geometry and uncertainty in deep learning for computer vision." Thesis, University of Cambridge, 2019. https://www.repository.cam.ac.uk/handle/1810/287944.
Full textAbstract:
Deep learning and convolutional neural networks have become the dominant tool for computer vision. These techniques excel at learning complicated representations from data using supervised learning. In particular, image recognition models now out-perform human baselines under constrained settings. However, the science of computer vision aims to build machines which can see. This requires models which can extract richer information than recognition, from images and video. In general, applying these deep learning models from recognition to other problems in computer vision is significantly more challenging. This thesis presents end-to-end deep learning architectures for a number of core computer vision problems; scene understanding, camera pose estimation, stereo vision and video semantic segmentation. Our models outperform traditional approaches and advance state-of-the-art on a number of challenging computer vision benchmarks. However, these end-to-end models are often not interpretable and require enormous quantities of training data. To address this, we make two observations: (i) we do not need to learn everything from scratch, we know a lot about the physical world, and (ii) we cannot know everything from data, our models should be aware of what they do not know. This thesis explores these ideas using concepts from geometry and uncertainty. Specifically, we show how to improve end-to-end deep learning models by leveraging the underlying geometry of the problem. We explicitly model concepts such as epipolar geometry to learn with unsupervised learning, which improves performance. Secondly, we introduce ideas from probabilistic modelling and Bayesian deep learning to understand uncertainty in computer vision models. We show how to quantify different types of uncertainty, improving safety for real world applications.
25
Weideman, Ryan. "Robot Navigation in Cluttered Environments with Deep Reinforcement Learning." DigitalCommons@CalPoly, 2019. https://digitalcommons.calpoly.edu/theses/2011.
Full textAbstract:
The application of robotics in cluttered and dynamic environments provides a wealth of challenges. This thesis proposes a deep reinforcement learning based system that determines collision free navigation robot velocities directly from a sequence of depth images and a desired direction of travel. The system is designed such that a real robot could be placed in an unmapped, cluttered environment and be able to navigate in a desired direction with no prior knowledge. Deep Q-learning, coupled with the innovations of double Q-learning and dueling Q-networks, is applied. Two modifications of this architecture are presented to incorporate direction heading information that the reinforcement learning agent can utilize to learn how to navigate to target locations while avoiding obstacles. The performance of the these two extensions of the D3QN architecture are evaluated in simulation in simple and complex environments with a variety of common obstacles. Results show that both modifications enable the agent to successfully navigate to target locations, reaching 88% and 67% of goals in a cluttered environment, respectively.
26
Janagam, Anirudh, and Saddam Hossen. "Analysis of Network Intrusion Detection System with Machine Learning Algorithms (Deep Reinforcement Learning Algorithm)." Thesis, Blekinge Tekniska Högskola, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-17126.
Full text
27
Mukhtar, Hind. "Machine Learning Enabled-Localization in 5G and LTE Using Image Classification and Deep Learning." Thesis, Université d'Ottawa / University of Ottawa, 2021. http://hdl.handle.net/10393/42449.
Full textAbstract:
Demand for localization has been growing due to the increase in location-based services and high bandwidth applications requiring precise localization of users to improve resource management and beam forming. Outdoor localization has been traditionally done through Global Positioning System (GPS), however it’s performance degrades in urban settings due to obstruction and multi-path effects, creating the need for better localization techniques. This thesis proposes a technique using a cascaded approach composed of image classification and deep learning using LIDAR or satellite images and Channel State In-formation (CSI) data from base stations to predict the location of moving vehicles and users outdoors. The algorithm’s performance is assessed using 3 different datasets. The first two use simulated data in the Milli-meter Wave (mmWave) band and lidar images that are collected from the neighbourhood of Rosslyn in Arlington, Virginia. The results show an improvement in localization accuracy as a result of the hierarchical architecture, with a Mean Absolute Error (MAE) of 6.55m for the proposed technique in comparison to a MAE of 9.82m using one Convolutional Neural Network (CNN). The third dataset uses measurements from an LTE mobile communication system along with satellite images that take place at the University of Denmark. The results achieve a MAE of 9.45 m fort he heirchichal approach in comparison to a MAE of 15.74 m for one Feed-Forward Neural Network (FFNN).
28
Moosavi, Seyedeh Samira. "Fingerprint-based localization in massive MIMO systems using machine learning and deep learning methods." Doctoral thesis, Université Laval, 2021. http://hdl.handle.net/20.500.11794/69511.
Full textAbstract:
À mesure que les réseaux de communication sans fil se développent vers la 5G, une énorme quantité de données sera produite et partagée sur la nouvelle plate-forme qui pourra être utilisée pour promouvoir de nouveaux services. Parmis ceux-ci, les informations de localisation des terminaux mobiles (MT) sont remarquablement utiles. Par exemple, les informations de localisation peuvent être utilisées dans différents cas de services d'enquête et d'information, de services communautaires, de suivi personnel, ainsi que de communications sensibles à la localisation. De nos jours, bien que le système de positionnement global (GPS) des MT offre la possibilité de localiser les MT, ses performances sont médiocres dans les zones urbaines où une ligne de vue directe (LoS) aux satellites est bloqué avec de nombreux immeubles de grande hauteur. En outre, le GPS a une consommation d'énergie élevée. Par conséquent, les techniques de localisation utilisant la télémétrie, qui sont basées sur les informations de signal radio reçues des MT tels que le temps d'arrivée (ToA), l'angle d'arrivée (AoA) et la réception de la force du signal (RSS), ne sont pas en mesure de fournir une localisation de précision satisfaisante. Par conséquent, il est particulièrement difficile de fournir des informations de localisation fiables des MT dans des environnements complexes avec diffusion et propagation par trajets multiples. Les méthodes d'apprentissage automatique basées sur les empreintes digitales (FP) sont largement utilisées pour la localisation dans des zones complexes en raison de leur haute fiabilité, rentabilité et précision et elles sont flexibles pour être utilisées dans de nombreux systèmes. Dans les réseaux 5G, en plus d'accueillir plus d'utilisateurs à des débits de données plus élevés avec une meilleure fiabilité tout en consommant moins d'énergie, une localisation de haute précision est également requise. Pour relever un tel défi, des systèmes massifs à entrées multiples et sorties multiples (MIMO) ont été introduits dans la 5G en tant que technologie puissante et potentielle pour non seulement améliorer l'efficacité spectrale et énergétique à l'aide d'un traitement relativement simple, mais également pour fournir les emplacements précis des MT à l'aide d'un très grand nombre d'antennes associées à des fréquences porteuses élevées. Il existe deux types de MIMO massifs (M-MIMO), soit distribué et colocalisé. Ici, nous visons à utiliser la méthode basée sur les FP dans les systèmes M-MIMO pour fournir un système de localisation précis et fiable dans un réseau sans fil 5G. Nous nous concentrons principalement sur les deux extrêmes du paradigme M-MIMO. Un grand réseau d'antennes colocalisé (c'est-à-dire un MIMO massif colocalisé) et un grand réseau d'antennes géographiquement distribué (c'est-à-dire un MIMO massif distribué). Ensuite, nous ex trayons les caractéristiques du signal et du canal à partir du signal reçu dans les systèmes M-MIMO sous forme d'empreintes digitales et proposons des modèles utilisant les FP basés sur le regroupement et la régression pour estimer l'emplacement des MT. Grâce à cette procédure, nous sommes en mesure d'améliorer les performances de localisation de manière significative et de réduire la complexité de calcul de la méthode basée sur les FP.As wireless communication networks are growing into 5G, an enormous amount of data will be produced and shared on the new platform, which can be employed in promoting new services. Location information of mobile terminals (MTs) is remarkably useful among them, which can be used in different use cases of inquiry and information services, community services, personal tracking, as well as location-aware communications. Nowadays, although the Global Positioning System (GPS) offers the possibility to localize MTs, it has poor performance in urban areas where a direct line-of-sight (LoS) to the satellites is blocked by many tall buildings. Besides, GPS has a high power consumption. Consequently, the ranging based localization techniques, which are based on radio signal information received from MTs such as time-of-arrival (ToA), angle-of-arrival (AoA), and received signal strength (RSS), are not able to provide satisfactory localization accuracy. Therefore, it is a notably challenging problem to provide precise and reliable location information of MTs in complex environments with rich scattering and multipath propagation. Fingerprinting (FP)-based machine learning methods are widely used for localization in complex areas due to their high reliability, cost-efficiency, and accuracy and they are flexible to be used in many systems. In 5G networks, besides accommodating more users at higher data rates with better reliability while consuming less power, high accuracy localization is also required in 5G networks. To meet such a challenge, massive multiple-input multiple-output (MIMO) systems have been introduced in 5G as a powerful and potential technology to not only improve spectral and energy efficiency using relatively simple processing but also provide an accurate locations of MTs using a very large number of antennas combined with high carrier frequencies. There are two types of massive MIMO (M-MIMO), distributed and collocated. Here, we aim to use the FP-based method in M-MIMO systems to provide an accurate and reliable localization system in a 5G wireless network. We mainly focus on the two extremes of the M-MIMO paradigm. A large collocated antenna array (i.e., collocated M-MIMO ) and a large geographically distributed antenna array (i.e., distributed M-MIMO). Then, we extract signal and channel features from the received signal in M-MIMO systems as fingerprints and propose FP-based models using clustering and regression to estimate MT's location. Through this procedure, we are able to improve localization performance significantly and reduce the computational complexity of the FP-based method.
29
Cabrera, Dalmazzo David. "Machine learning and deep neural networks approach to modelling musical gestures." Doctoral thesis, Universitat Pompeu Fabra, 2020. http://hdl.handle.net/10803/670399.
Full textAbstract:
Gestures can be defined as a form of non-verbal communication associated with an intention or an emotional state articulation. They are not only intrinsically part of the human language, but also explain specific details of a body-knowledge execution. Gestures are being studied not only in the language research field but also in dance, sports, rehabilitation, and music; where the term is understood as a “learned technique of the body”. Therefore, in music education, gestures are assumed as automatic-motor abilities learned by repetitional practice, to self-teach and fine-tune the motor actions optimally. Hence, those gestures are intended to be part of the performer’s technical repertoire to take fast actions/decisions on-the flight, assuming that they are not only relevant in music expressive capabilities but also, a method for a correct ‘energy-consumption’ habit development to avoid injuries.
In this thesis, we applied state-of-the-art machine learning (ML) techniques to model violin bowing gestures in professional players. Concretely, we recorded a database of expert performers and different student levels and developed three strategies to classify and recognise those gestures in real-time: a) First, we developed a multimodal synchronisation system to record audio, video and IMU sensor data with a unified time reference. We programmed a custom C++ application to visualise the output from the ML models. We implemented a Hidden Markov Model to detect fingering disposition and bow-stroke gesture performance. b) A second approach is a system that extracts general time features from the gestures samples, creating a dataset of audio and motion data from expert performers implementing a Deep Neural Networks algorithm. To do so, we have implemented the hybrid model CNN LSTM architecture. c) Furthermore, a Melspectrogram based analysis that can read and extract patterns from only audio data, opening the option of recognising relevant information from the audio recordings without the need for external sensors to achieve similar results. All of these techniques are complementary and also incorporated into an education application as a computer assistant to enhance music-learners practice by providing useful real-time feedback. The application will be tested in a professional education institution.Els gestos es poden definir com una forma de comunicació no verbal associada a una intenció o a l’articulació d’un estat emocional. No només formen part intrínsecament del llenguatge humà, sinó que també expliquen detalls específics de l’execució del coneixement del cos. Els gestos són objecte d’estudi no només en el camp de la recerca lingüística, sinó també en la dansa, l’esport, la rehabilitació i la música; on el terme s’entén com a “tècnica apresa del cos”. Per tant, en l’educació musical, els gestos s’assumeixen com a habilitats automomotrius apreses mitjançant la pràctica repetitiva, per aprendre i ajustar les accions motrius de manera ptima. En conseqüència, aquests gestos estan destinats a formar part del repertori tècnic de l’intèrpret per prendre accions/decisions ràpides en temps real durant la interpretació, suposant que no només són rellevants en les capacitats expressives de la música, sinó que també ho són com a mètode per a un correcte desenvolupament d’hàbits (“çonsum d’energia”) per evitar lesions. En aquesta tesi, hem aplicat tècniques de Machine Learning (ML) d’última generació per modelar els gestos de proa de violí en músics professionals. Concretament, hem enregistrat una base de dades d’intèrprets experts i d’estudiants de diferents nivells i hem desenvolupat tres estratègies per classificar i reconèixer aquests gestos en temps real: a) Primer, hem desenvolupar un sistema de sincronització multimodal per enregistrar dades de sensors d’àudio, vídeo i IMU amb una referència de tamps unificada. Hem programat una aplicació C++ per visualitzar els resultats dels models ML. Hem implementat un Hidden Markov Model per detectar la disposició dels dits i la realització de gestos de l’arc. b) Un segon enfocament aplicatés un sistema que extreu les característiques generals de les seqüències de dades de les mostres de gestos, creant un conjunt de dades d’àudio i de dades de moviment d’intèrprets experts implementant un algoritme de Deep Neural Networks. Per fer-ho, hem aplicat el model híbrid d’arquitectura CNN-LSTM. c) A més, s’ha fet una anàlisi basada en l’espectrograma Mel que pot llegir i extreure patrons només de dades d’àudio, obrint l’opció de reconèixer informació rellevant dels enregistraments d’àudio sense necessitat de sensors externs per obtenir resultats similars. Totes aquestes tècniques són complementàries i s’han incorporat a una aplicació d’educació com a assistent d’ordinador per millorar la pràctica dels aprenents de música proporcionant comentaris útils en temps real. Aquesta aplicació serà provada en una institució d’educació professional.
Los gestos pueden definirse como una forma de comunicación no verbal asociada con una intención o una articulación del estado emocional. No solo forman parte intrínsec del lenguaje humano, sino que también explican detalles específicos de la ejecución del conocimiento corporal. Los gestos se están estudiando no solo en el campo de la investigación del lenguaje, sino también en danza, deportes, rehabilitación y música; donde el término se entiende como una “técnica aprendida del cuerpo”. Por tanto, en la educación musical, los gestos se asumen como habilidades motoras automáticas aprendidas mediante la práctica repetitiva, para aprender y afinar las acciones motoras de forma óptima. Por lo tanto, esos gestos están destinados a ser parte del repertorio técnico del intérprete para tomar acciones/decisiones rápidas en tiempo real, asumiendo que no solo son relevantes en las capacidades expresivas de la música sino también, como un método para desarrollar hábitos correctos de 'consumo de energía’ para evitar lesiones. En esta tesis, aplicamos técnicas de Machine Learning (ML) de última generación para modelar los gestos de arco de violín en interpretes profesionales. Concretamente, creamos una base de datos con músicos expertos y también con diferentes niveles de estudiantes, desarrollando tres estrategias para clasificar y reconocer esos gestos en tiempo real: a) Primero, desarrollamos un sistema de sincronización multimodal para grabar audio, video y datos de sensores IMU con una referencia de tiempo unificada. Programamos una aplicación C++ personalizada para visualizar el resultado de los modelos ML. Implementamos un Hidden Markov Model para detectar la disposición de los dedos y la ejecución del gestos del arco. b) Desarrollamos un sistema que extrae características de tiempo generales en todas las muestras de gestos, creando un conjunto de datos de audio y datos de movimiento de músicos expertos implementando un algoritmo Deep neural Networks; particularmente, el modelo híbrido CNN-LSTM. c) Además, un análisis basado en espectrograma Mel que puede leer y extraer patrones únicamente usando datos de audio, abriendo la opción de reconocer información relevante usando las grabaciones de audio sin la necesidad de sensores externos para lograr resultados similares. Todas estas técnicas son complementarias y también se incorporan en una aplicación educativa como asistente computacional para mejorar la práctica de los estudiantes de música, al proporcionar información útil en tiempo real. La aplicación se probará en una institución de educación profesional.
30
Valeriana, Riccardo. "Deep Learning: Algoritmo di Classificazione Immagini." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/17557/.
Full textAbstract:
La presente tesi si occupa della descrizione dell’algoritmo di Deep Learning che permette la classificazione di immagini importate dal dataset CIFAR-10. Il codice è stato testato in un ambiente di test per un classificatore di immagini per piattaforme Apple macOS, dove sono state utilizzate immagini di frutta e verdura come input per la classificazione.
Nel primo capitolo viene trattato il dataset CIFAR-10, come questo è stato realizzato, la sua struttura e l’uso che se ne può fare. Successivamente viene descritto il metodo di apprendimento automatico della Classificazione Lineare, in che cosa consiste, come agisce nella suddivisione di classi e quali vantaggi e svantaggi comporta. Segue l’introduzione di metodologie di apprendimento supervisionato note come macchine a vettori di supporto (SVM o Support Vector Machines) sfruttate per la classificazione di pattern e la definizione della funzione Score, che viene utilizzata per determinare la classe a cui appartiene ciascuna immagine.
Nel secondo capitolo viene trattato il Deep Learning e le Reti Neurali (non convoluzionali), modello matematico basato sulla riproduzione approssimata della struttura neuronale biologica, il cervello dei mammiferi, in particolare relativamente al funzionamento della corteccia visiva.
Il terzo e ultimo capitolo tratta in modo più approfondito e tecnico l’implementazione di un algoritmo di Deep Learning sviluppato in Pytorch, assieme alla libreria di Numpy, spiegando passo per passo come questo è stato strutturato. Infine viene osservato come un classificatore di immagini per piattaforme macOS opera con figure eterogenee raccolte da internet di verdure e frutti.
31
Potuaud, Sylvain. "Human Grasp Synthesis with Deep Learning." Thesis, KTH, Robotik, perception och lärande, RPL, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-229915.
Full textAbstract:
The human hands are one of the most complex organs of the human body. As they enable us to grasp various objects in many different ways, they have played a crucial role in the rise of the human race. Being able to control hands as a human do is a key step towards friendly human-robots interaction and realistic virtual human simulations. Grasp generation has been mostly studied for the purpose of generating physically stable grasps. This paper addresses a different aspect: how to generate realistic, natural looking grasps that are similar to human grasps. To simplify the problem, the wrist position is assumed to be known and only the finger pose is generated. As the realism of a grasp is not easy to put into equations, data-driven machine learning techniques are used. This paper investigated the application of the deep neural networks to the grasp generation problems. Two different object shape representations (point cloud and multi-view depth images), and multiple network architectures are experimented, using a collected human grasping dataset in a virtual reality environment. The resulting generated grasps are highly realistic and human-like. Though there are sometimes some finger penetrations on the object surface, the general poses of the fingers around the grasped objects are similar to the collected human data. The good performance extends to the objects of categories previously unseen by the network. This work has validated the efficiency of a data-driven deep learning approach for human-like grasp synthesis. I believe the realistic-looking objective of the grasp synthesis investigated in this thesis can be combined with the existing mechanical, stable grasp criteria to achieve both natural-looking and reliable grasp generations.Den mänskliga handen är en av de mest komplexa organen i människokroppen. Eftersom våra händer gör det möjligt för oss att hantera olika föremål på många olika sätt, har de spelat en avgörande roll i människans utveckling. Att kunna styra händer är ett viktigt steg mot interaktion mellan människor och robotar, samt skapa realistiska simuleringar av virtuella människor. Virtualla handgrepp har tidigare mest studerats för att generera fysiskt stabila grepp. I detta papper behandlas en annan aspekt: hur man genererar realistiska grepp som liknar en människas grepp. För att förenkla problemet antas att handledspositionen är känd och endast fingerkonfigurationen genereras. Eftersom hur realistiskt ett grepp är inte är lätt att beskriva i ekvationer, används istället data-driven maskininlärningsteknik. Detta papper undersöker tillämpningen av djupa neurala nätverken (Deep Neural Networks) för att generera grepp. Två olika representationer av former i 3D (punktmoln och bilder med djupinformation) och flera alternativa nätverksarkitekturer utvärderas med hjälp av en databas av mänskliga grepp samlad i en virtuell verklighetsmiljö. De resulterande genererade greppen är mycket realistiska och mänskliga. Även om det ibland förekommer något finger som penetrerar objektet, liknar den allmänna positioneringen av fingrarna den insamlade mänskliga datan. Denna goda prestanda gäller även för föremål i kategorier som aldrig tidigare setts av nätverket. I arbetet valideras också effektiviteten av ett data-drivet tillvägagångssätt baserat på djupa neurala nätverk för människoliknande syntes av grepp
32
Halle, Alex, and Alexander Hasse. "Topologieoptimierung mittels Deep Learning." Technische Universität Chemnitz, 2019. https://monarch.qucosa.de/id/qucosa%3A34343.
Full textAbstract:
Die Topologieoptimierung ist die Suche einer optimalen Bauteilgeometrie in Abhängigkeit des Einsatzfalls. Für komplexe Probleme kann die Topologieoptimierung aufgrund eines hohen Detailgrades viel Zeit- und Rechenkapazität erfordern. Diese Nachteile der Topologieoptimierung sollen mittels Deep Learning reduziert werden, so dass eine Topologieoptimierung dem Konstrukteur als sekundenschnelle Hilfe dient. Das Deep Learning ist die Erweiterung künstlicher neuronaler Netzwerke, mit denen Muster oder Verhaltensregeln erlernt werden können. So soll die bislang numerisch berechnete Topologieoptimierung mit dem Deep Learning Ansatz gelöst werden. Hierzu werden Ansätze, Berechnungsschema und erste Schlussfolgerungen vorgestellt und diskutiert.
33
Yan, Jie Lu. "Development and validation of deep learning classifiers for antimicrobial peptide prediction." Thesis, University of Macau, 2018. http://umaclib3.umac.mo/record=b3881886.
Full text
34
Hesamifard, Ehsan. "Privacy Preserving Machine Learning as a Service." Thesis, University of North Texas, 2020. https://digital.library.unt.edu/ark:/67531/metadc1703277/.
Full textAbstract:
Machine learning algorithms based on neural networks have achieved remarkable results and are being extensively used in different domains. However, the machine learning algorithms requires access to raw data which is often privacy sensitive. To address this issue, we develop new techniques to provide solutions for running deep neural networks over encrypted data. In this paper, we develop new techniques to adopt deep neural networks within the practical limitation of current homomorphic encryption schemes. We focus on training and classification of the well-known neural networks and convolutional neural networks. First, we design methods for approximation of the activation functions commonly used in CNNs (i.e. ReLU, Sigmoid, and Tanh) with low degree polynomials which is essential for efficient homomorphic encryption schemes. Then, we train neural networks with the approximation polynomials instead of original activation functions and analyze the performance of the models. Finally, we implement neural networks and convolutional neural networks over encrypted data and measure performance of the models.
35
Solenne, Andrea. "Machine Learning nell'era del Digital Marketing." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020. http://amslaurea.unibo.it/20476/.
Full textAbstract:
Il Machine Learning è una branca dell’intelligenza artificiale avente lo scopo di migliorare autonomamente l’identificazione di pattern nei dati. L'obiettivo di questo elaborato è capire se gli strumenti che mette a disposizine il machine learning possano fare la differenza nella creazione di strategie di digital marketing. Per rispondere a questa domanda sono stati presi in considerazione come casi studio, aziende che hanno utilizzato o utilizzano algoritmi di machine learning per il raggiungimento o miglioramento delle proprie strategie di marketing. Sulla base dei casi analizzati, si è dedotto che tali algoritmi non solo migliorano queste strategie ma bensì ne identificano di nuove, proponendo previsioni sempre più accurate a chi le utilizza.
36
Berry, Jeffrey James. "Machine Learning Methods for Articulatory Data." Diss., The University of Arizona, 2012. http://hdl.handle.net/10150/223348.
Full textAbstract:
Humans make use of more than just the audio signal to perceive speech. Behavioral and neurological research has shown that a person's knowledge of how speech is produced influences what is perceived. With methods for collecting articulatory data becoming more ubiquitous, methods for extracting useful information are needed to make this data useful to speech scientists, and for speech technology applications. This dissertation presents feature extraction methods for ultrasound images of the tongue and for data collected with an Electro-Magnetic Articulograph (EMA). The usefulness of these features is tested in several phoneme classification tasks. Feature extraction methods for ultrasound tongue images presented here consist of automatically tracing the tongue surface contour using a modified Deep Belief Network (DBN) (Hinton et al. 2006), and methods inspired by research in face recognition which use the entire image. The tongue tracing method consists of training a DBN as an autoencoder on concatenated images and traces, and then retraining the first two layers to accept only the image at runtime. This 'translational' DBN (tDBN) method is shown to produce traces comparable to those made by human experts. An iterative bootstrapping procedure is presented for using the tDBN to assist a human expert in labeling a new data set. Tongue contour traces are compared with the Eigentongues method of (Hueber et al. 2007), and a Gabor Jet representation in a 6-class phoneme classification task using Support Vector Classifiers (SVC), with Gabor Jets performing the best. These SVC methods are compared to a tDBN classifier, which extracts features from raw images and classifies them with accuracy only slightly lower than the Gabor Jet SVC method.For EMA data, supervised binary SVC feature detectors are trained for each feature in three versions of Distinctive Feature Theory (DFT): Preliminaries (Jakobson et al. 1954), The Sound Pattern of English (Chomsky and Halle 1968), and Unified Feature Theory (Clements and Hume 1995). Each of these feature sets, together with a fourth unsupervised feature set learned using Independent Components Analysis (ICA), are compared on their usefulness in a 46-class phoneme recognition task. Phoneme recognition is performed using a linear-chain Conditional Random Field (CRF) (Lafferty et al. 2001), which takes advantage of the temporal nature of speech, by looking at observations adjacent in time. Results of the phoneme recognition task show that Unified Feature Theory performs slightly better than the other versions of DFT. Surprisingly, ICA actually performs worse than running the CRF on raw EMA data.
37
Adams, William A. "Analysis of Robustness in Lane Detection using Machine Learning Models." Ohio University / OhioLINK, 2015. http://rave.ohiolink.edu/etdc/view?acc_num=ohiou1449167611.
Full text
38
Ridolfi, Federico. "Applicazioni di deep learning per CAD mammografico." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2016. http://amslaurea.unibo.it/12264/.
Full textAbstract:
Il tumore alla mammella è ad oggi una delle principali cause di mortalità femminile e, sebbene attualmente la medicina offra una buona possibilità di guarigione, l'arma più potente contro questa particolare neoplasia è la prevenzione, svolta in particolare tramite programmi di screening mammografici sui pazienti in fasce d'età a rischio.
Dall'esigenza di massimizzare l'efficenza di tali pratiche nascono i CAD (Computer Assisted Diagnosis), pacchetti software in grado di affiancare lo specialista nell'analisi del referto medico aiutandolo ad identificare e localizzare la patologia. I moderni CAD si basano sulle tecniche più avanzate di machine learning.
In questo lavoro si discuterà della nuova rete CaffeNet_MAMMO, un prototipo di sistema CAD, basato su reti neurali a convoluzione (CNN) e del suo addestramento sul database MiniMIAS. Una delle caratteristiche peculiari del metodo qui illustrato è la capacità di fornire risultati comparabili ad altri metodi CAD basati su classificatori CNN monostato (pur rimanendo al di sotto dei prodotti commerciali) nonostante l'addestramento sia stato svolto su un database di ridotte dimensioni, normalmente insufficiente per dare risultati accettabili su siffatta architettura.
Il metodo proposto risulta estremamente promettente, portando a un classificatore con un'efficienza AUC pari a 0.68 +- 0.08, con una specificità e una sensibilità fino al 70% , che corrisponde alla fascia alta dei classificatori appartenenti alla stessa famiglia. Viene altresì proposta una bozza di algoritmo di localizzazione della patologia, il quale, sebbene lontano dagli standard di riferimento, riesce ad identificare con sufficiente precisione le patologie presenti nelle immagini proposte. Tuttavia l'algoritmo di localizzazione presenta una specificità insufficiente per un'applicazione sul campo allo stato attuale, risultando comunque un interessante punto di partenza per futuri lavori.
39
Bearzotti, Riccardo. "Structural damage detection using deep learning networks." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018.
Find full textAbstract:
Research on damage detection of structures using image process- ing techniques has been actively conducted, specially on infrastruc- tures as road pavements, achieving considerably high detection accu- racies.
These techniques are more and more studied all over the world cause seems be a powerful method able to replace, in some conditions, the experience and the visual ability of humans.
This thesis has the purpose to introduce how the development in the last few years of the image processing can be useful to avoid some costs on structure monitoring and predict some disaster, that the most of times we listened call them as announced disasters that could be avoided.
This thesis introduce the deep learning method implemented on Mat- lab to solve this problems trying to understand, in the first part, what machine learning and deep learning consist of, which is the best way to use the convolution neural networks and in which parameters work on. This we the purpose to give some background about this tech- nique in order to implement it on a large number of problems. There will be also some examples of basic codes and the outcomes are discussed, in order to figure out which is the best tool or combi- nation of tool to solve a problem of more complexity.
At the end there are some consideration about useful future works that can be studied in order to help in structure monitoring in lab tests, during the life cycle and in case of collapse.
40
Wang, Qianlong. "Blockchain-Empowered Secure Machine Learning and Applications." Case Western Reserve University School of Graduate Studies / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=case1625183576139299.
Full text
41
Zhang, Yi. "NOVEL APPLICATIONS OF MACHINE LEARNING IN BIOINFORMATICS." UKnowledge, 2019. https://uknowledge.uky.edu/cs_etds/83.
Full textAbstract:
Technological advances in next-generation sequencing and biomedical imaging have led to a rapid increase in biomedical data dimension and acquisition rate, which is challenging the conventional data analysis strategies. Modern machine learning techniques promise to leverage large data sets for finding hidden patterns within them, and for making accurate predictions. This dissertation aims to design novel machine learning-based models to transform biomedical big data into valuable biological insights. The research presented in this dissertation focuses on three bioinformatics domains: splice junction classification, gene regulatory network reconstruction, and lesion detection in mammograms.
A critical step in defining gene structures and mRNA transcript variants is to accurately identify splice junctions. In the first work, we built the first deep learning-based splice junction classifier, DeepSplice. It outperforms the state-of-the-art classification tools in terms of both classification accuracy and computational efficiency. To uncover transcription factors governing metabolic reprogramming in non-small-cell lung cancer patients, we developed TFmeta, a machine learning approach to reconstruct relationships between transcription factors and their target genes in the second work. Our approach achieves the best performance on benchmark data sets. In the third work, we designed deep learning-based architectures to perform lesion detection in both 2D and 3D whole mammogram images.
42
Ishaq, Omer. "Image Analysis and Deep Learning for Applications in Microscopy." Doctoral thesis, Uppsala universitet, Avdelningen för visuell information och interaktion, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-283846.
Full textAbstract:
Quantitative microscopy deals with the extraction of quantitative measurements from samples observed under a microscope. Recent developments in microscopy systems, sample preparation and handling techniques have enabled high throughput biological experiments resulting in large amounts of image data, at biological scales ranging from subcellular structures such as fluorescently tagged nucleic acid sequences to whole organisms such as zebrafish embryos. Consequently, methods and algorithms for automated quantitative analysis of these images have become increasingly important. These methods range from traditional image analysis techniques to use of deep learning architectures. Many biomedical microscopy assays result in fluorescent spots. Robust detection and precise localization of these spots are two important, albeit sometimes overlapping, areas for application of quantitative image analysis. We demonstrate the use of popular deep learning architectures for spot detection and compare them against more traditional parametric model-based approaches. Moreover, we quantify the effect of pre-training and change in the size of training sets on detection performance. Thereafter, we determine the potential of training deep networks on synthetic and semi-synthetic datasets and their comparison with networks trained on manually annotated real data. In addition, we present a two-alternative forced-choice based tool for assisting in manual annotation of real image data. On a spot localization track, we parallelize a popular compressed sensing based localization method and evaluate its performance in conjunction with different optimizers, noise conditions and spot densities. We investigate its sensitivity to different point spread function estimates. Zebrafish is an important model organism, attractive for whole-organism image-based assays for drug discovery campaigns. The effect of drug-induced neuronal damage may be expressed in the form of zebrafish shape deformation. First, we present an automated method for accurate quantification of tail deformations in multi-fish micro-plate wells using image analysis techniques such as illumination correction, segmentation, generation of branch-free skeletons of partial tail-segments and their fusion to generate complete tails. Later, we demonstrate the use of a deep learning-based pipeline for classifying micro-plate wells as either drug-affected or negative controls, resulting in competitive performance, and compare the performance from deep learning against that from traditional image analysis approaches.
43
Airola, Rasmus, and Kristoffer Hager. "Image Classification, Deep Learning and Convolutional Neural Networks : A Comparative Study of Machine Learning Frameworks." Thesis, Karlstads universitet, Institutionen för matematik och datavetenskap, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kau:diva-55129.
Full textAbstract:
The use of machine learning and specifically neural networks is a growing trend in software development, and has grown immensely in the last couple of years in the light of an increasing need to handle big data and large information flows. Machine learning has a broad area of application, such as human-computer interaction, predicting stock prices, real-time translation, and self driving vehicles. Large companies such as Microsoft and Google have already implemented machine learning in some of their commercial products such as their search engines, and their intelligent personal assistants Cortana and Google Assistant. The main goal of this project was to evaluate the two deep learning frameworks Google TensorFlow and Microsoft CNTK, primarily based on their performance in the training time of neural networks. We chose to use the third-party API Keras instead of TensorFlow's own API when working with TensorFlow. CNTK was found to perform better in regards of training time compared to TensorFlow with Keras as frontend. Even though CNTK performed better on the benchmarking tests, we found Keras with TensorFlow as backend to be much easier and more intuitive to work with. In addition, CNTKs underlying implementation of the machine learning algorithms and functions differ from that of the literature and of other frameworks. Therefore, if we had to choose a framework to continue working in, we would choose Keras with TensorFlow as backend, even though the performance is less compared to CNTK.
44
Wallis, David. "A study of machine learning and deep learning methods and their application to medical imaging." Thesis, université Paris-Saclay, 2021. http://www.theses.fr/2021UPAST057.
Full textAbstract:
Nous utilisons d'abord des réseaux neuronaux convolutifs (CNNs) pour automatiser la détection des ganglions lymphatiques médiastinaux dans les images TEP/TDM. Nous construisons un modèle entièrement automatisé pour passer directement des images TEP/TDM à la localisation des ganglions. Les résultats montrent une performance comparable à celle d'un médecin. Dans la seconde partie de la thèse, nous testons la performance, l'interprétabilité et la stabilité des modèles radiomiques et CNN sur trois ensembles de données (IRM cérébrale 2D, TDM pulmonaire 3D, TEP/TDM médiastinale 3D). Nous comparons la façon dont les modèles s'améliorent lorsque davantage de données sont disponibles et nous examinons s'il existe des tendances communess aux différents problèmes. Nous nous demandons si les méthodes actuelles d'interprétation des modèles sont satisfaisantes. Nous étudions également comment une segmentation précise affecte les performances des modèles. Nous utilisons d'abord des réseaux neuronaux convolutifs (CNNs) pour automatiser la détection des ganglions lymphatiques médiastinaux dans les images TEP/TDM. Nous construisons un modèle entièrement automatisé pour passer directement des images TEP/TDM à la localisation des ganglions. Les résultats montrent une performance comparable à celle d'un médecin. Dans la seconde partie de la thèse, nous testons la performance, l'interprétabilité et la stabilité des modèles radiomiques et CNN sur trois ensembles de données (IRM cérébrale 2D, TDM pulmonaire 3D, TEP/TDM médiastinale 3D). Nous comparons la façon dont les modèles s'améliorent lorsque davantage de données sont disponibles et nous examinons s'il existe des tendances communess aux différents problèmes. Nous nous demandons si les méthodes actuelles d'interprétation des modèles sont satisfaisantes. Nous étudions également comment une segmentation précise affecte les performances des modèlesWe first use Convolutional Neural Networks (CNNs) to automate mediastinal lymph node detection using FDG-PET/CT scans. We build a fully automated model to go directly from whole-body FDG-PET/CT scans to node localisation. The results show a comparable performance to an experienced physician. In the second half of the thesis we experimentally test the performance, interpretability, and stability of radiomic and CNN models on three datasets (2D brain MRI scans, 3D CT lung scans, 3D FDG-PET/CT mediastinal scans). We compare how the models improve as more data is available and examine whether there are patterns common to the different problems. We question whether current methods for model interpretation are satisfactory. We also investigate how precise segmentation affects the performance of the models. We first use Convolutional Neural Networks (CNNs) to automate mediastinal lymph node detection using FDG-PET/CT scans. We build a fully automated model to go directly from whole-body FDG-PET/CT scans to node localisation. The results show a comparable performance to an experienced physician. In the second half of the thesis we experimentally test the performance, interpretability, and stability of radiomic and CNN models on three datasets (2D brain MRI scans, 3D CT lung scans, 3D FDG-PET/CT mediastinal scans). We compare how the models improve as more data is available and examine whether there are patterns common to the different problems. We question whether current methods for model interpretation are satisfactory. We also investigate how precise segmentation affects the performance of the models
45
Houmadi, Sherri F. "THE APPLICATION OF CONVOLUTIONAL NEURAL NETWORKS TO CLASSIFY PAINT DEFECTS." OpenSIUC, 2020. https://opensiuc.lib.siu.edu/dissertations/1807.
Full textAbstract:
AN ABSTRACT OF THE DISSERTATION OFSherri Houmadi, for the Doctor of Philosophy degree in Engineering Science, presented on March 27, 2020, at Southern Illinois University Carbondale. TITLE: THE APPLICATION OF CONVOLUTIONAL NEURAL NETWORKS TO CLASSIFY PAINT DEFECTSMAJOR PROFESSOR: Dr. Julie DunstonDespite all of the technological advancements in computer vision, many companies still utilize human visual inspection to determine whether parts are good or bad. It is particularly challenging for humans to inspect parts in a fast-moving manufacturing environment. Such is the case at Aisin Manufacturing Illinois where this study will be testing the use of convolutional neural networks (CNNs) to classify paint defects on painted outside door handles and caps for automobiles. Widespread implementation of vision systems has resulted in advancements in machine learning. As the field of artificial intelligence (AI) evolves and improvement are made, diverse industries are adopting AI models for use in their applications. Medical imaging classification using neural networks has exploded in recent years. Convolutional neural networks have proven to scale very well for image classification models by extracting various features from the images. A goal of this study is to create a low-cost machine learning model that is able to quickly classify paint defects in order to identify rework parts that can be repaired and shipped. The central thesis of this doctoral work is to test a machine learning model that can classify the paint defects based on a very small dataset of images, where the images are taken with a smartphone camera in a manufacturing setting. The end goal is to train the model for an overall accuracy rate of at least 80%. By using transfer learning and balancing the class datasets, the model was trained to achieve an overall accuracy rate of 82%.
46
Li, Zheng. "Assessing Structure–Property Relationships of Crystal Materials using Deep Learning." Thesis, Virginia Tech, 2020. http://hdl.handle.net/10919/99488.
Full textAbstract:
In recent years, deep learning technologies have received huge attention and interest in the field of high-performance material design. This is primarily because deep learning algorithms in nature have huge advantages over the conventional machine learning models in processing massive amounts of unstructured data with high performance. Besides, deep learning models are capable of recognizing the hidden patterns among unstructured data in an automatic fashion without relying on excessive human domain knowledge. Nevertheless, constructing a robust deep learning model for assessing materials' structure-property relationships remains a non-trivial task due to highly flexible model architecture and the challenge of selecting appropriate material representation methods. In this regard, we develop advanced deep-learning models and implement them for predicting the quantum-chemical calculated properties (i.e., formation energy) for an enormous number of crystal systems. Chapter 1 briefly introduces some fundamental theory of deep learning models (i.e., CNN, GNN) and advanced analysis methods (i.e., saliency map). In Chapter 2, the convolutional neural network (CNN) model is established to find the correlation between the physically intuitive partial electronic density of state (PDOS) and the formation energies of crystals. Importantly, advanced machine learning analysis methods (i.e., salience mapping analysis) are utilized to shed light on underlying physical factors governing the energy properties. In Chapter 3, we introduce the methodology of implementing the cutting-edge graph neural networks (GNN) models for learning an enormous number of crystal structures for the desired properties.Master of Science
Machine learning technologies, particularly deep learning, have demonstrated remarkable progress in facilitating the high-throughput materials discovery process. In essence, machine learning algorithms have the ability to uncover the hidden patterns of data and make appropriate decisions without being explicitly programmed. Nevertheless, implementing machine learning models in the field of material design remains a challenging task. One of the biggest limitations is our insufficient knowledge about the structure-property relationships for material systems. As the performance of machine learning models is to a large degree determined by the underlying material representation method, which typically requires the experts to have in-depth knowledge of the material systems. Thus, designing effective feature representation methods is always the most crucial aspect for machine learning model development and the process takes a significant amount of manual effort. Even though tremendous efforts have been made in recent years, the research process for robust feature representation methods is still slow. In this regard, we attempt to automate the feature engineering process with the assistance of advanced deep learning algorithms. Unlike the conventional machine learning models, our deep learning models (i.e., convolutional neural networks, graph neural networks) are capable of processing massive amounts of structured data such as spectrum and crystal graphs. Specifically, the deep learning models are explicitly designed to learn the hidden latent variables that are contained in crystal structures in an automatic fashion and provide accurate prediction results. We believe the deep learning models have huge potential to simplify the machine learning modeling process and facilitate the discovery of promising functional materials.
47
Conciatori, Marco. "tecniche di deep learning applicate a giochi atari." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19132/.
Full textAbstract:
La presente tesi è incentrata sulla progettazione e sperimentazione di varianti per l'algoritmo DQN, diffusamente utilizzato per affrontare problemi di reinforcement learning con reti neurali. L'obbiettivo prefissato consiste nel migliorarne le performance, soprattutto nel caso degli ambienti a ricompense sparse.
Nell'ambito di questi problemi infatti gli algoritmi di reinforcement learning, tra cui lo stesso DQN, incontrano difficoltà nel conseguimento di risultati soddisfacenti.
Le modifiche apportate all'algoritmo hanno lo scopo di ottimizzarne le modalità di apprendimento, seguendo, in estrema sintesi, due principali direzioni: un miglior sfruttamento delle poche ricompense a disposizione attraverso un loro più frequente utilizzo, oppure una esplorazione più efficace, ad esempio tramite l'introduzione di scelta casuale delle mosse e/o dell'entropia.
Si ottengono in questo modo diverse versioni di DQN che vengono poi confrontate fra loro e con l'algoritmo originale sulla base dei risultati ottenuti.
48
Mancevo, del Castillo Ayala Diego. "Compressing Deep Convolutional Neural Networks." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-217316.
Full textAbstract:
Deep Convolutional Neural Networks and "deep learning" in general stand at the cutting edge on a range of applications, from image based recognition and classification to natural language processing, speech and speaker recognition and reinforcement learning. Very deep models however are often large, complex and computationally expensive to train and evaluate. Deep learning models are thus seldom deployed natively in environments where computational resources are scarce or expensive. To address this problem we turn our attention towards a range of techniques that we collectively refer to as "model compression" where a lighter student model is trained to approximate the output produced by the model we wish to compress. To this end, the output from the original model is used to craft the training labels of the smaller student model. This work contains some experiments on CIFAR-10 and demonstrates how to use the aforementioned techniques to compress a people counting model whose precision, recall and F1-score are improved by as much as 14% against our baseline.
49
Hussain, Jabbar. "Deep Learning Black Box Problem." Thesis, Uppsala universitet, Institutionen för informatik och media, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-393479.
Full textAbstract:
Application of neural networks in deep learning is rapidly growing due to their ability to outperform other machine learning algorithms in different kinds of problems. But one big disadvantage of deep neural networks is its internal logic to achieve the desired output or result that is un-understandable and unexplainable. This behavior of the deep neural network is known as “black box”. This leads to the following questions: how prevalent is the black box problem in the research literature during a specific period of time? The black box problems are usually addressed by socalled rule extraction. The second research question is: what rule extracting methods have been proposed to solve such kind of problems? To answer the research questions, a systematic literature review was conducted for data collection related to topics, the black box, and the rule extraction. The printed and online articles published in higher ranks journals and conference proceedings were selected to investigate and answer the research questions. The analysis unit was a set of journals and conference proceedings articles related to the topics, the black box, and the rule extraction. The results conclude that there has been gradually increasing interest in the black box problems with the passage of time mainly because of new technological development. The thesis also provides an overview of different methodological approaches used for rule extraction methods.
50
Castaño-Candamil, Sebastián [Verfasser], and Michael W. [Akademischer Betreuer] Tangermann. "Machine learning methods for motor performance decoding in adaptive deep brain stimulation." Freiburg : Universität, 2020. http://d-nb.info/1224808762/34.
Full text