Log in

Relevant bibliographies by topics / Deep Convontional Neural Network / Dissertations / Theses

To see the other types of publications on this topic, follow the link: Deep Convontional Neural Network.

Dissertations / Theses on the topic 'Deep Convontional Neural Network'

Author: Grafiati

Published: 5 June 2025

Last updated: 2 August 2025

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 dissertations / theses for your research on the topic 'Deep Convontional Neural Network.'

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

Kapoor, Rishika. "Malaria Detection Using Deep Convolution Neural Network." University of Cincinnati / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1613749143868579.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

Pajot, Arthur. "Incorporating physical knowledge into deep neural network." Electronic Thesis or Diss., Sorbonne université, 2019. http://www.theses.fr/2019SORUS290.

Full text

Abstract:

Un processus physique est un phénomène marqué par des changements graduels à travers une série d'états successifs se produisant dans le monde physique. Les physiciens et les climatologues tentent de modéliser ces processus d'une manière fondée sur le principe de descriptions analytiques des connaissances a priori des processus sous-jacents. Malgré le succès indéniable de l'apprentissage profond, une approche entièrement axée sur les données n'est pas non plus encore prête à remettre en question l'approche classique de modélisation des systèmes dynamiques. Nous tenterons de démontrer dans cette

APA, Harvard, Vancouver, ISO, and other styles

3

Heuillet, Alexandre. "Exploring deep neural network differentiable architecture design." Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPASG069.

Full text

Abstract:

L'intelligence artificielle (IA) a gagné en popularité ces dernières années, principalement en raison de ses applications réussies dans divers domaines tels que l'analyse de données textuelles, la vision par ordinateur et le traitement audio. La résurgence des techniques d'apprentissage profond a joué un rôle central dans ce succès. L'article révolutionnaire de Krizhevsky et al., AlexNet, a réduit l'écart entre les performances humaines et celles des machines dans les tâches de classification d'images. Des articles ultérieurs tels que Xception et ResNet ont encore renforcé l'apprentissage prof

APA, Harvard, Vancouver, ISO, and other styles

4

Verma, Sagar. "Deep Neural Network Modeling of Electric Motors." Electronic Thesis or Diss., université Paris-Saclay, 2023. http://www.theses.fr/2023UPAST088.

Full text

Abstract:

Cette thèse traite de l’application des réseaux de neurones dans la résolution de problèmes liés aux moteurs électriques. Le chapitre 2 contribue à identiﬁer une structure de réseau de neurones capable d’apprendre la relation multi-variée entre diﬀérents signaux d’un moteur électrique. La structure identiﬁée est ensuite utilisée pour l’estimation vitesse- couple à partir des courants et des tensions.Le chapitre 3 se concentre sur la détection et la correction de défauts de mesure. Notre méthode prend en compte les défauts de capteurs électriques, les défauts mécaniques et l’estimation de tempé

APA, Harvard, Vancouver, ISO, and other styles

5

Dupont, Robin. "Deep Neural Network Compression for Visual Recognition." Electronic Thesis or Diss., Sorbonne université, 2023. http://www.theses.fr/2023SORUS565.

Full text

Abstract:

Grâce à la miniaturisation de l'électronique, les dispositifs embarqués sont devenus omniprésents depuis les années 2010, réalisant diverses tâches autour de nous. À mesure que leur utilisation augmente, la demande pour des dispositifs traitant les données et prenant des décisions complexes de manière efficace s'intensifie. Les réseaux de neurones profonds sont puissants pour cet objectif, mais souvent trop lourds pour les appareils embarqués. Il est donc impératif de compresser ces réseaux sans compromettre leur performance. Cette thèse introduit deux méthodes innovantes centrées sur l'élagag

APA, Harvard, Vancouver, ISO, and other styles

6

Aspandi, Latif Decky. "Deep spatio-temporal neural network for facial analysis." Doctoral thesis, Universitat Pompeu Fabra, 2021. http://hdl.handle.net/10803/671209.

Full text

Abstract:

Automatic Facial Analysis is one of the most important field of computer vision due to its significant impacts to the world we currently live in. Among many applications of Automatic Facial Analysis, Facial Alignment and Facial-Based Emotion Recognition are two most prominent tasks considering their roles in this field. That is, the former serves as intermediary steps enabling many higher facial analysis tasks, and the latter provides direct, real-world high level facial-based analysis and applications to the society. Together, they have significant impacts ranging from biometric recognition,

APA, Harvard, Vancouver, ISO, and other styles

7

Alpire, Adam. "Predicting Solar Radiation using a Deep Neural Network." Thesis, KTH, Skolan för informations- och kommunikationsteknik (ICT), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-215715.

Full text

Abstract:

Simulating the global climate in fine granularity is essential in climate science research. Current algorithms for computing climate models are based on mathematical models that are computationally expensive. Climate simulation runs can take days or months to execute on High Performance Computing (HPC) platforms. As such, the amount of computational resources determines the level of resolution for the simulations. If simulation time could be reduced without compromising model fidelity, higher resolution simulations would be possible leading to potentially new insights in climate science resear

APA, Harvard, Vancouver, ISO, and other styles

8

Redkar, Shrutika. "Deep Learning Binary Neural Network on an FPGA." Digital WPI, 2017. https://digitalcommons.wpi.edu/etd-theses/407.

Full text

Abstract:

In recent years, deep neural networks have attracted lots of attentions in the field of computer vision and artificial intelligence. Convolutional neural network exploits spatial correlations in an input image by performing convolution operations in local receptive fields. When compared with fully connected neural networks, convolutional neural networks have fewer weights and are faster to train. Many research works have been conducted to further reduce computational complexity and memory requirements of convolutional neural networks, to make it applicable to low-power embedded applications. T

APA, Harvard, Vancouver, ISO, and other styles

9

Shuvo, Md Kamruzzaman. "Hardware Efficient Deep Neural Network Implementation on FPGA." OpenSIUC, 2020. https://opensiuc.lib.siu.edu/theses/2792.

Full text

Abstract:

In recent years, there has been a significant push to implement Deep Neural Networks (DNNs) on edge devices, which requires power and hardware efficient circuits to carry out the intensive matrix-vector multiplication (MVM) operations. This work presents hardware efficient MVM implementation techniques using bit-serial arithmetic and a novel MSB first computation circuit. The proposed designs take advantage of the pre-trained network weight parameters, which are already known in the design stage. Thus, the partial computation results can be pre-computed and stored into look-up tables. Then the

APA, Harvard, Vancouver, ISO, and other styles

10

Sarpangala, Kishan. "Semantic Segmentation Using Deep Learning Neural Architectures." University of Cincinnati / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ucin157106185092304.

Full text

APA, Harvard, Vancouver, ISO, and other styles

11

Huang, Shimin. "Cross-Layer Congestion Control with Deep Neural Network in Cellular Network." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-264239.

Full text

Abstract:

A significant fraction of data traffic is transmitted via cellular networks. When introducing fifth-generation (5G) radio access technology, the maximum bitrate of the radio link increases significantly, and the delay is lowered. Network congestion occurs when the sender attempts to send data at a higher rate than the network link or nodes can handle. In order to improve the performance of the mobile networks, many congestion control techniques and approaches have been developed over the years. Varying radio conditions in mobile networks make it challenging to indicate the occurrence of the co

APA, Harvard, Vancouver, ISO, and other styles

12

Wu, Chunyang. "Structured deep neural networks for speech recognition." Thesis, University of Cambridge, 2018. https://www.repository.cam.ac.uk/handle/1810/276084.

Full text

Abstract:

Deep neural networks (DNNs) and deep learning approaches yield state-of-the-art performance in a range of machine learning tasks, including automatic speech recognition. The multi-layer transformations and activation functions in DNNs, or related network variations, allow complex and difficult data to be well modelled. However, the highly distributed representations associated with these models make it hard to interpret the parameters. The whole neural network is commonly treated a ``black box''. The behaviours of activation functions and the meanings of network parameters are rarely controlle

APA, Harvard, Vancouver, ISO, and other styles

13

Samuelsson, Elin. "A Confidence Measure for Deep Convolutional Neural Network Regressors." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-273967.

Full text

Abstract:

Deep convolutional neural networks can be trained to estimate gaze directions from eye images. However, such networks do not provide any information about the reliability of its predictions. As uncertainty estimates could enable more accurate and reliable gaze tracking applications, a method for confidence calculation was examined in this project. This method had to be computationally efficient for the gaze tracker to function in real-time, without reducing the quality of the gaze predictions. Thus, several state-of-the-art methods were abandoned in favor of Mean-Variance Estimation, which use

APA, Harvard, Vancouver, ISO, and other styles

14

Fu, Zehua. "Confidence measures in deep neural network based stereo matching." Thesis, Lyon, 2020. http://www.theses.fr/2020LYSEC014.

Full text

Abstract:

Malgré des décennies d’amélioration depuis la première proposition de Barnard et Fischler, les approches d’appariement stéréo souffrent encore d’imprécision, notamment en présence d’occlusion, des conditions d’éclairage extrêmes et d’ambiguïté. Pour pallier ces imprécisions, de nombreuses méthodes, appelées mesures de confiance, ont été proposées permettant d’évaluer l’exactitude des appariements. Dans cette thèse, nous étudions les mesures de confiance de l’état de l’art et proposons deux mesures, à bases de réseaux neurones et d’apprentissage profond, permettant d’améliorer les performances

APA, Harvard, Vancouver, ISO, and other styles

15

Li, Qing. "Medical image analysis with neural network and deep learning." Thesis, The University of Sydney, 2016. http://hdl.handle.net/2123/14940.

Full text

Abstract:

Thanks to the advance of biomedical imaging systems, large volumes of biomedical image data are generated rapidly. However many doctors still rely on time consuming manual inspection of the patients’ medical images to make diagnostic decisions. There is growing interest from medical and biology researchers to develop automated tools and algorithms that can efficiently extract and utilize useful information from large scale biomedical image databases. Artificial Neural Networks (ANN) have proved very successful in various machine learning and artificial intelligence areas. Recent advances in n

APA, Harvard, Vancouver, ISO, and other styles

16

Khan, Muhammad Jazib. "Programmable Address Generation Unit for Deep Neural Network Accelerators." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-271884.

Full text

Abstract:

The Convolutional Neural Networks are getting more and more popular due to their applications in revolutionary technologies like Autonomous Driving, Biomedical Imaging, and Natural Language Processing. With this increase in adoption, the complexity of underlying algorithms is also increasing. This trend entails implications for the computation platforms as well, i.e. GPUs, FPGA, or ASIC based accelerators, especially for the Address Generation Unit (AGU), which is responsible for the memory access. Existing accelerators typically have Parametrizable Datapath AGUs, which have minimal adaptabili

APA, Harvard, Vancouver, ISO, and other styles

17

Lopes, André Teixeira. "Facial expression recognition using deep learning - convolutional neural network." Universidade Federal do Espírito Santo, 2016. http://repositorio.ufes.br/handle/10/4301.

Full text

Abstract:

Made available in DSpace on 2016-08-29T15:33:24Z (GMT). No. of bitstreams: 1 tese_9629_dissertacao(1)20160411-102533.pdf: 9277551 bytes, checksum: c18df10308db5314d25f9eb1543445b3 (MD5) Previous issue date: 2016-03-03<br>CAPES<br>O reconhecimento de expressões faciais tem sido uma área de pesquisa ativa nos últimos dez anos, com uma área de aplicação em crescimento como animação de personagens e neuro-marketing. O reconhecimento de uma expressão facial não é um problema fácil para métodos de aprendizagem de máquina, dado que pessoas diferentes podem variar na forma com que mostram suas exp

APA, Harvard, Vancouver, ISO, and other styles

18

Nagarajan, Santhosh Kumar. "Server-Less Rule-Based Chatbot Using Deep Neural Network." Thesis, Uppsala universitet, Institutionen för informationsteknologi, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-395931.

Full text

Abstract:

Customer support entails multi-faceted benefits for IT businesses. Presently, the business depends upon on conventional channels like e-mail, customer care and web interface to provide customer support services. However, with the advent of new developments in Scania IT, different IT business units is driving a shift towards automated chatbot solutions to provide flexible responses to the user's questions. This thesis presents a practical study of such chatbot solution for the company SCANIA CV AB, Södertälje. The objective of the research work presented in this thesis is to analyze several dee

APA, Harvard, Vancouver, ISO, and other styles

19

Malek, Salim. "Deep neural network models for image classification and regression." Doctoral thesis, Università degli studi di Trento, 2018. https://hdl.handle.net/11572/368992.

Full text

Abstract:

Deep learning, a branch of machine learning, has been gaining ground in many research fields as well as practical applications. Such ongoing boom can be traced back mainly to the availability and the affordability of potential processing facilities, which were not widely accessible than just a decade ago for instance. Although it has demonstrated cutting-edge performance widely in computer vision, and particularly in object recognition and detection, deep learning is yet to find its way into other research areas. Furthermore, the performance of deep learning models has a strong dependency on t

APA, Harvard, Vancouver, ISO, and other styles

20

Malek, Salim. "Deep neural network models for image classification and regression." Doctoral thesis, University of Trento, 2018. http://eprints-phd.biblio.unitn.it/2961/1/These_final02.pdf.

Full text

Abstract:

Deep learning, a branch of machine learning, has been gaining ground in many research fields as well as practical applications. Such ongoing boom can be traced back mainly to the availability and the affordability of potential processing facilities, which were not widely accessible than just a decade ago for instance. Although it has demonstrated cutting-edge performance widely in computer vision, and particularly in object recognition and detection, deep learning is yet to find its way into other research areas. Furthermore, the performance of deep learning models has a strong dependency on t

APA, Harvard, Vancouver, ISO, and other styles

21

Ullah, I. "A PYRAMIDAL APPROACH FOR DESIGNING DEEP NEURAL NETWORK ARCHITECTURES." Doctoral thesis, Università degli Studi di Milano, 2017. http://hdl.handle.net/2434/466758.

Full text

Abstract:

Developing an intelligent system, capable of learning discriminative high-level features from high dimensional data lies at the core of solving many computer vision (CV ) and machine learning (ML) tasks. Scene or human action recognition from videos is an important topic in CV and ML. Its applications include video surveillance, robotics, human-computer interaction, video retrieval, etc. Several bio inspired hand crafted feature extraction systems have been proposed for processing temporal data. However, recent deep learning techniques have dominated CV and ML by their good performance on larg

APA, Harvard, Vancouver, ISO, and other styles

22

Ayoub, Issa. "Multimodal Affective Computing Using Temporal Convolutional Neural Network and Deep Convolutional Neural Networks." Thesis, Université d'Ottawa / University of Ottawa, 2019. http://hdl.handle.net/10393/39337.

Full text

Abstract:

Affective computing has gained significant attention from researchers in the last decade due to the wide variety of applications that can benefit from this technology. Often, researchers describe affect using emotional dimensions such as arousal and valence. Valence refers to the spectrum of negative to positive emotions while arousal determines the level of excitement. Describing emotions through continuous dimensions (e.g. valence and arousal) allows us to encode subtle and complex affects as opposed to discrete emotions, such as the basic six emotions: happy, anger, fear, disgust, sad and n

APA, Harvard, Vancouver, ISO, and other styles

23

Chen, Tairui. "Going Deeper with Convolutional Neural Network for Intelligent Transportation." Digital WPI, 2016. https://digitalcommons.wpi.edu/etd-theses/144.

Full text

Abstract:

Over last several decades, computer vision researchers have been devoted to find good feature to solve different tasks, object recognition, object detection, object segmentation, activity recognition and so forth. Ideal features transform raw pixel intensity values to a representation in which these computer vision problems are easier to solve. Recently, deep feature from covolutional neural network(CNN) have attracted many researchers to solve many problems in computer vision. In the supervised setting, these hierarchies are trained to solve specific problems by minimizing an objective functi

APA, Harvard, Vancouver, ISO, and other styles

24

Wang, Xutao. "Chinese Text Classification Based On Deep Learning." Thesis, Mittuniversitetet, Avdelningen för informationssystem och -teknologi, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-35322.

Full text

Abstract:

Text classification has always been a concern in area of natural language processing, especially nowadays the data are getting massive due to the development of internet. Recurrent neural network (RNN) is one of the most popular method for natural language processing due to its recurrent architecture which give it ability to process serialized information. In the meanwhile, Convolutional neural network (CNN) has shown its ability to extract features from visual imagery. This paper combine the advantages of RNN and CNN and proposed a model called BLSTM-C for Chinese text classification. BLSTM-C

APA, Harvard, Vancouver, ISO, and other styles

25

Зайяд, Абдаллах Мухаммед. "Ecrypted Network Classification With Deep Learning." Master's thesis, КПІ ім. Ігоря Сікорського, 2020. https://ela.kpi.ua/handle/123456789/34069.

Full text

Abstract:

Дисертація складається з 84 сторінок, 59 Цифри та 29 джерел у довідковому списку. Проблема: Оскільки світ стає більш безпечним, для забезпечення належної передачі даних між сторонами, що спілкуються, було використано більше протоколів шифрування. Класифікація мережі стала більше клопоту з використанням деяких прийомів, оскільки перевірка зашифрованого трафіку в деяких країнах може бути незаконною. Це заважає інженерам мережі мати можливість класифікувати трафік, щоб відрізняти зашифрований від незашифрованого трафіку. Мета роботи: Ця стаття спрямована на проблему, спричинену попередні

APA, Harvard, Vancouver, ISO, and other styles

26

Li, Dongfu. "Deep Neural Network Approach for Single Channel Speech Enhancement Processing." Thesis, Université d'Ottawa / University of Ottawa, 2016. http://hdl.handle.net/10393/34472.

Full text

Abstract:

Speech intelligibility represents how comprehensible a speech is. It is more important than speech quality in some applications. Single channel speech intelligibility enhancement is much more difficult than multi-channel intelligibility enhancement. It has recently been reported that training-based single channel speech intelligibility enhancement algorithms perform better than Signal to Noise Ratio (SNR) based algorithm. In this thesis, a training-based Deep Neural Network (DNN) is used to improve single channel speech intelligibility. To increase the performance of the DNN, the Multi-Resolut

APA, Harvard, Vancouver, ISO, and other styles

27

Thangthai, Kwanchiva. "Computer lipreading via hybrid deep neural network hidden Markov models." Thesis, University of East Anglia, 2018. https://ueaeprints.uea.ac.uk/69215/.

Full text

Abstract:

Constructing a viable lipreading system is a challenge because it is claimed that only 30% of information of speech production is visible on the lips. Nevertheless, in small vocabulary tasks, there have been several reports of high accuracies. However, investigation of larger vocabulary tasks is rare. This work examines constructing a large vocabulary lipreading system using an approach based-on Deep Neural Network Hidden Markov Models (DNN-HMMs). We present the historical development of computer lipreading technology and the state-ofthe-art results in small and large vocabulary tasks. In prel

APA, Harvard, Vancouver, ISO, and other styles

28

Kabore, Raogo. "Hybrid deep neural network anomaly detection system for SCADA networks." Thesis, Ecole nationale supérieure Mines-Télécom Atlantique Bretagne Pays de la Loire, 2020. http://www.theses.fr/2020IMTA0190.

Full text

Abstract:

Les systèmes SCADA sont de plus en plus ciblés par les cyberattaques en raison de nombreuses vulnérabilités dans le matériel, les logiciels, les protocoles et la pile de communication. Ces systèmes utilisent aujourd'hui du matériel, des logiciels, des systèmes d'exploitation et des protocoles standard. De plus, les systèmes SCADA qui étaient auparavant isolés sont désormais interconnectés aux réseaux d'entreprise et à Internet, élargissant ainsi la surface d'attaque. Dans cette thèse, nous utilisons une approche deep learning pour proposer un réseau de neurones profonds hybride efficace pour l

APA, Harvard, Vancouver, ISO, and other styles

29

Popli, Labhesh. "AN ATTENTION BASED DEEP NEURAL NETWORK FOR VISUAL QUESTIONANSWERING SYSTEM." Cleveland State University / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=csu1579015180507068.

Full text

APA, Harvard, Vancouver, ISO, and other styles

30

Tran, Khanh-Hung. "Semi-supervised dictionary learning and Semi-supervised deep neural network." Thesis, université Paris-Saclay, 2021. http://www.theses.fr/2021UPASP014.

Full text

Abstract:

Depuis les années 2010, l’apprentissage automatique (ML) est l’un des sujets qui retient beaucoup l'attention des chercheurs scientifiques. De nombreux modèles de ML ont démontré leur capacité produire d’excellent résultats dans des divers domaines comme Vision par ordinateur, Traitement automatique des langues, Robotique… Toutefois, la plupart de ces modèles emploient l’apprentissage supervisé, qui requiert d’un massive annotation. Par conséquent, l’objectif de cette thèse est d’étudier et de proposer des approches semi-supervisées qui ont plusieurs avantages par rapport à l’apprentissage sup

APA, Harvard, Vancouver, ISO, and other styles

31

SENG, Kruy. "Cost-sensitive deep neural network ensemble for class imbalance problem." Digital Commons @ Lingnan University, 2018. https://commons.ln.edu.hk/otd/32.

Full text

Abstract:

In data mining, classification is a task to build a model which classifies data into a given set of categories. Most classification algorithms assume the class distribution of data to be roughly balanced. In real-life applications such as direct marketing, fraud detection and churn prediction, class imbalance problem usually occurs. Class imbalance problem is referred to the issue that the number of examples belonging to a class is significantly greater than those of the others. When training a standard classifier with class imbalance data, the classifier is usually biased toward majority clas

APA, Harvard, Vancouver, ISO, and other styles

32

Fornander, Hannes. "Denoising Monte Carlo Dose Calculations Using a Deep Neural Network." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-263096.

Full text

Abstract:

This thesis explores the possibility of using a deep neural network (DNN) to denoise Monte Carlo dose calculations for external beam radiotherapy. The dose distributions considered here are for inhomogeneous materials such as those of the human body. The purpose of the project is to explore whether a DNN is able to preserve important features of the dose distributions as well as to evaluate if there is a potential performance gain of using a DNN compared to the traditional approach of running a full Monte Carlo simulation. The network architecture considered in this thesis is a 3D version of t

APA, Harvard, Vancouver, ISO, and other styles

33

Abrishami, Hedayat. "Deep Learning Based Electrocardiogram Delineation." University of Cincinnati / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1563525992210273.

Full text

APA, Harvard, Vancouver, ISO, and other styles

34

Martinini, Filippo. "Deep Neural Recovery For Compressed Imaging." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021. http://amslaurea.unibo.it/22431/.

Full text

Abstract:

One of the biggest problem of MRI is its long scan time. To speed up the acquisition is possible to reduce the acquired points and reconstruct the missing ones after the acquisition. This work is based on a novel approach called LOUPE that tackles at same time the problem of reconstruction and the problem of finding the best under-sampling pattern. We contribute by adding some improvements to LOUPE. We introduce a regularization term, called "Flashback" that weights the difference of the under-sampled input with respect to its reconstructed version and improves the whole training performances.

APA, Harvard, Vancouver, ISO, and other styles

35

Parakkal, Sreenivasan Akshai. "Deep learning prediction of Quantmap clusters." Thesis, Uppsala universitet, Institutionen för biologisk grundutbildning, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-445909.

Full text

Abstract:

The hypothesis that similar chemicals exert similar biological activities has been widely adopted in the field of drug discovery and development. Quantitative Structure-Activity Relationship (QSAR) models have been used ubiquitously in drug discovery to understand the function of chemicals in biological systems. A common QSAR modeling method calculates similarity scores between chemicals to assess their biological function. However, due to the fact that some chemicals can be similar and yet have different biological activities, or conversely can be structurally different yet have similar biolo

APA, Harvard, Vancouver, ISO, and other styles

36

Chen, Zhe. "Augmented Context Modelling Neural Networks." Thesis, The University of Sydney, 2019. http://hdl.handle.net/2123/20654.

Full text

Abstract:

Contexts provide beneficial information for machine-based image understanding tasks. However, existing context modelling methods still cannot fully exploit contexts, especially for object recognition and detection. In this thesis, we develop augmented context modelling neural networks to better utilize contexts for different object recognition and detection tasks. Our contributions are two-fold: 1) we introduce neural networks to better model instance-level visual relationships; 2) we introduce neural network-based algorithms to better utilize contexts from 3D information and synthesized data

APA, Harvard, Vancouver, ISO, and other styles

37

Squadrani, Lorenzo. "Deep neural networks and thermodynamics." Bachelor's thesis, Alma Mater Studiorum - Università di Bologna, 2020.

Find full text

Abstract:

Deep learning is the most effective and used approach to artificial intelligence, and yet it is far from being properly understood. The understanding of it is the way to go to further improve its effectiveness and in the best case to gain some understanding of the "natural" intelligence. We attempt a step in this direction with the aim of physics. We describe a convolutional neural network for image classification (trained on CIFAR-10) within the descriptive framework of Thermodynamics. In particular we define and study the temperature of each component of the network. Our results provides a n

APA, Harvard, Vancouver, ISO, and other styles

38

Watcharapichat, Pijika. "Improving the performance of dataflow systems for deep neural network training." Thesis, Imperial College London, 2017. http://hdl.handle.net/10044/1/57955.

Full text

Abstract:

Deep neural networks (DNNs) have led to significant advancements in machine learning. With deep structure and flexible model parameterisation, they exhibit state-of-the-art accuracies for many complex tasks e.g. image recognition. To achieve this, models are trained iteratively over large datasets. This process involves expensive matrix operations, making it time-consuming to obtain converged models. To accelerate training, dataflow systems parallelise computation. A scalable approach is to use parameter server framework: it has workers that train model replicas in parallel and parameter serve

APA, Harvard, Vancouver, ISO, and other styles

39

Shiu, Wei-Shiang, and 徐偉翔. "Dynamic Deep Neural Network Watermarking." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/dh28vz.

Full text

Abstract:

碩士<br>國立臺灣海洋大學<br>資訊工程學系<br>107<br>A well-trained deep neural network is an important intellectual property for owner(s). Embedding watermarks into deep neural networks can help to prove ownership while the deep neural network has been stealing. We propose a new deep neural network watermarking using the concept of software watermarking. We use a specific image as input data, and the watermark is used as the output when the neural network sees the input data. We establishes the unique association between the watermark and the neural network in a verified manner. The advantage of this method is

APA, Harvard, Vancouver, ISO, and other styles

40

Mohamed, Abdel-rahman. "Deep Neural Network Acoustic Models for ASR." Thesis, 2014. http://hdl.handle.net/1807/44123.

Full text

Abstract:

Automatic speech recognition (ASR) is a key core technology for the information age. ASR systems have evolved from discriminating among isolated digits to recognizing telephone-quality, spontaneous speech, allowing for a growing number of practical applications in various sectors. Nevertheless, there are still serious challenges facing ASR which require major improvement in almost every stage of the speech recognition process. Until very recently, the standard approach to ASR had remained largely unchanged for many years. It used Hidden Markov Models (HMMs) to model the sequential structure of

APA, Harvard, Vancouver, ISO, and other styles

41

Sun, Tzu-Chun, and 孫梓鈞. "Fruit Recognition Using Deep Convolution Neural Network." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/76315586416634324332.

Full text

Abstract:

碩士<br>國立暨南國際大學<br>資訊工程學系<br>102<br>This thesis focuses on developing a fruit recognition method. It can be used to improve life convenience by shortening the supermarket checkout time. Existing methods for fruit recognition use handcrafted image features, such as the texture, the color, and the shape of a fruit, for fruit recognition. However, image features extracted with a set of specific algorithms do not necessarily provide enough information for pattern recognition. In this work, we use deep convolution neural network (DCNN) to learn discriminative fruit features automatically. In order

APA, Harvard, Vancouver, ISO, and other styles

42

Lan, Jia-Shin, and 藍家馨. "Facial Attribute Detection by Deep Neural Network." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/27757791944778213699.

Full text

Abstract:

碩士<br>國立臺灣大學<br>資訊工程學研究所<br>104<br>Facial attributes have gained popularity in the past few years in machine vision tasks including recognition, classification, and retrieval. Predicting facial attributes from web images is very challenging due to background clutters and face variations, such as scale, pose, and illumination in the real world. The key to this problem is to build proper feature representations to cope with these unfavourable conditions. Given the success of deep neural network (DNN) in image classification, the high level DNN feature as an intuitive and reasonable choice has be

APA, Harvard, Vancouver, ISO, and other styles

43

張潤淋. "Deep neural network for graphic structure data." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/7jew2d.

Full text

Abstract:

碩士<br>逢甲大學<br>通訊工程學系<br>107<br>Convolutional neural networks are important network architectures for deep learning, and they have been widely used for pattern recognition with high accuracy. However, most of the data in reality are mostly Non-Euclidean Data. The general convolutional neural network cannot handle such data. In recent years, Graph Convolutional Neural Networks [10] [11] have been proposed for non-Euclidean data, as shown in the figure. The biggest advantage of the graph convolutional neural network is that it can analyze the data type of the graph form, allowing the input to be

APA, Harvard, Vancouver, ISO, and other styles

44

JEN, PO-CHUNG, and 任博仲. "Movie Trailer Classification with Deep Neural Network." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/tp4x7g.

Full text

Abstract:

碩士<br>中華大學<br>資訊工程學系<br>107<br>Learning movie contents for movie genre classification is a challenge study, traditional machine learning methods still now achieve unsatisfactory results. On the other hand, in the past few years, the rise of deep learning, one area of machine learning, significantly improved the accuracy of image recognition. Nevertheless, rather than image recognition, analyzing the contents by using a single image, movie genre classification usually requires the analysis of the contents of a series of image frames or a part of sound. Therefore, a deep learning based movie gen

APA, Harvard, Vancouver, ISO, and other styles

45

TIWARI, ANKIT. "CHARACTER RECOGNITION USING DEEP LEARNING NEURAL NETWORK." Thesis, 2017. http://dspace.dtu.ac.in:8080/jspui/handle/repository/15973.

Full text

Abstract:

OCR stands for Optical Character Recognition and is the mechanical or electronic translation of images consisting of text into the editable text. It is mostly used to convert handwritten(taken by scanner or by other means) into text. Human beings recognize many objects in this manner our eyes are the "optical mechanism." But while the brain "sees" the input, the ability to comprehend these signals varies in each person according to many factors. Digitization of text documents is often combined with the process of optical character recognition (OCR). Recognizing a character is a normal and easy

APA, Harvard, Vancouver, ISO, and other styles

46

Jhu, Jhe-Kuan, and 朱哲寬. "Face Detection Based on Deep Convolutional Neural Network." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/q9ubg6.

Full text

Abstract:

碩士<br>國立暨南國際大學<br>電機工程學系<br>105<br>The thesis is mainly to explore the problem of face detection. Face detection in the intelligent surveillance environment is a very important research topic. The CNN has been used to achieve face detection goals due to the global upsurge of DL in recent years. On this thesis, the algorithm consists two stages of detection. The first stage is to implement the method in literature [61] and then use the Head Pose Image Database for testing and remove the top 10 groups. Each group has 93 images and each image has different angles of the face image. The test resul

APA, Harvard, Vancouver, ISO, and other styles

47

Lin, Mei-Ling, and 林美伶. "Face Recognition using A Deep Convolutional Neural Network." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/2myacg.

Full text

Abstract:

碩士<br>國立中央大學<br>資訊工程學系<br>104<br>In recent years, face recognition and face detection techniques are widely used in various applications, such as access control systems, surveillance system, login system, and community websites etc. However, there are some factors that affect the recognition performance like different lighting conditions, facial expression, face rotation, and occlusion by other objects. In this paper, we use Multi-scale Block Local Binary Pattern (MB-LBP) to detect face. MB-LBP can overcome different lighting conditions, blurred and noise images. We add multi-angle face images

APA, Harvard, Vancouver, ISO, and other styles

48

Lin, Chi-hui, and 林季暉. "A Modified Deep Neural Network Speech Enhancement Model." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/8ncc39.

Full text

Abstract:

碩士<br>逢甲大學<br>資訊工程學系<br>104<br>Speech intelegibility is more essential than before due to more and more mobile devices need to improve speech quality. This paper develops a more efficient deep neural network (DNN) speech enhancement model based upon Y. Xu’s DNN speech enhancement model, but the structure of DNNs and the learning algorithm of MLPs are modified to achieve an efficient DNN learning. A deep MLP neural net is composed by unrolling a stack of RBMs and adding on a layer to the last stage of the MLP. In the last layer, each neuron has a linear activation function with initial identit

APA, Harvard, Vancouver, ISO, and other styles

49

Kuo, Hao-Yuan, and 郭皓元. "Mapping Deep Neural Network for Efficient FPGA Implementation." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/6t4scu.

Full text

Abstract:

碩士<br>國立臺灣大學<br>電子工程學研究所<br>105<br>Deploying deep neural networks (DNNs) in hardware is a common tactic to achieve energy, performance, and area efficiency for widespread applications. Binarizing neural networks is a key step to eliminate costly arithmetic computation from circuit implementation.Available neuron binarization methods are based on either special training or stochastic computation.The former requires expertise and experience to find a workable training procedure for a given network architecture;the latter decouples the training process and is generally and systematically applicab

APA, Harvard, Vancouver, ISO, and other styles

50

Liao, Tzu-Ting, and 廖姿婷. "3D depth ordering based on deep neural network." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/70311221488024446157.

Full text

Abstract:

碩士<br>國立交通大學<br>電子工程學系電子研究所<br>102<br>In this thesis, we propose a method to estimate 3-D depth map from a single image. Unlike approaches employing a geometric model behind the scene to infer the depth map, we propose to estimate the 3-D scenes by extracting local depth cues without any structure assumptions in the scene instead. In our approach, first we partition the image into several regions. We focus on inferring the depth ordering in a local patch. Then we apply the model of deep neural network to figure out which depth order class the local patch belong and to automatically learn the

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!