To see the other types of publications on this topic, follow the link: Artificial neural networks; Learning algorithms.
Dissertations / Theses on the topic 'Artificial neural networks; Learning algorithms'
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 'Artificial neural networks; Learning algorithms.'
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
Sannossian, Hermineh Y. "A study of artificial neural networks and their learning algorithms." Thesis, Loughborough University, 1992. https://dspace.lboro.ac.uk/2134/11194.
Full textAbstract:
The work presented in this thesis is mainly involved in the study of Artificial Neural Networks (ANNs) and their learning strategies. The ANN simulator incorporating the Backpropagation (BP) algorithm is designed and analysed and run on a MIMD parallel computer namely the Balance 8000 multiprocessor machine. Initially, an overview of the learning algorithms of ANNs are described. Some of the acceleration techniques including Heuristic methods for the BP like algorithms are introduced. The software design of the simulator for both On-line and Batch BP is described. Two different strategies for parallelism are considered and the results of the speedups of both algorithms are compared. Later a Heuristic algorithm (GRBH) for accelerating the BP method is introduced and the results are compared with the BP using a variety of expositing examples. The simulator is used to train networks for invariant character recognition using moments. The trained networks are tested for different examples and the results are analysed. The thesis concludes with a chapter summarizing the main results and suggestions for further study.
2
Ghosh, Ranadhir, and n/a. "A Novel Hybrid Learning Algorithm For Artificial Neural Networks." Griffith University. School of Information Technology, 2003. http://www4.gu.edu.au:8080/adt-root/public/adt-QGU20030808.162355.
Full textAbstract:
Last few decades have witnessed the use of artificial neural networks (ANN) in many real-world applications and have offered an attractive paradigm for a broad range of adaptive complex systems. In recent years ANN have enjoyed a great deal of success and have proven useful in wide variety pattern recognition or feature extraction tasks. Examples include optical character recognition, speech recognition and adaptive control to name a few. To keep the pace with its huge demand in diversified application areas, many different kinds of ANN architecture and learning types have been proposed by the researchers to meet varying needs. A novel hybrid learning approach for the training of a feed-forward ANN has been proposed in this thesis. The approach combines evolutionary algorithms with matrix solution methods such as singular value decomposition, Gram-Schmidt etc., to achieve optimum weights for hidden and output layers. The proposed hybrid method is to apply evolutionary algorithm in the first layer and least square method (LS) in the second layer of the ANN. The methodology also finds optimum number of hidden neurons using a hierarchical combination methodology structure for weights and architecture. A learning algorithm has many facets that can make a learning algorithm good for a particular application area. Often there are trade offs between classification accuracy and time complexity, nevertheless, the problem of memory complexity remains. This research explores all the different facets of the proposed new algorithm in terms of classification accuracy, convergence property, generalization ability, time and memory complexity.
3
Chen, Hsinchun. "Machine Learning for Information Retrieval: Neural Networks, Symbolic Learning, and Genetic Algorithms." Wiley Periodicals, Inc, 1995. http://hdl.handle.net/10150/106427.
Full textAbstract:
Artificial Intelligence Lab, Department of MIS, University of ArizonaInformation retrieval using probabilistic techniques has attracted significant attention on the part of researchers in information and computer science over the past few decades. In the 1980s, knowledge-based techniques also made an impressive contribution to “intelligent” information retrieval and indexing. More recently, information science researchers have turned to other newer artificial-intelligence- based inductive learning techniques including neural networks, symbolic learning, and genetic algorithms. These newer techniques, which are grounded on diverse paradigms, have provided great opportunities for researchers to enhance the information processing and retrieval capabilities of current information storage and retrieval systems. In this article, we first provide an overview of these newer techniques and their use in information science research. To familiarize readers with these techniques, we present three popular methods: the connectionist Hopfield network; the symbolic ID3/ID5R; and evolution- based genetic algorithms. We discuss their knowledge representations and algorithms in the context of information retrieval. Sample implementation and testing results from our own research are also provided for each technique. We believe these techniques are promising in their ability to analyze user queries, identify users’ information needs, and suggest alternatives for search. With proper user-system interactions, these methods can greatly complement the prevailing full-text, keywordbased, probabilistic, and knowledge-based techniques.
4
Bubie, Walter C. "Algorithm animation and its application to artificial neural network learning /." Online version of thesis, 1991. http://hdl.handle.net/1850/11055.
Full text
5
Hofer, Daniel G. Sbarbaro. "Connectionist feedforward networks for control of nonlinear systems." Thesis, University of Glasgow, 1992. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.390248.
Full text
6
Khalid, Fahad. "Measure-based Learning Algorithms : An Analysis of Back-propagated Neural Networks." Thesis, Blekinge Tekniska Högskola, Avdelningen för för interaktion och systemdesign, 2008. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-4795.
Full textAbstract:
In this thesis we present a theoretical investigation of the feasibility of using a problem specific inductive bias for back-propagated neural networks. We argue that if a learning algorithm is biased towards optimizing a certain performance measure, it is plausible to assume that it will generate a higher performance score when evaluated using that particular measure. We use the term measure function for a multi-criteria evaluation function that can also be used as an inherent function in learning algorithms, in order to customize the bias of a learning algorithm for a specific problem. Hence, the term measure-based learning algorithms. We discuss different characteristics of the most commonly used performance measures and establish similarities among them. The characteristics of individual measures and the established similarities are then correlated to the characteristics of the backpropagation algorithm, in order to explore the applicability of introducing a measure function to backpropagated neural networks. Our study shows that there are certain characteristics of the error back-propagation mechanism and the inherent gradient search method that limit the set of measures that can be used for the measure function. Also, we highlight the significance of taking the representational bias of the neural network into account when developing methods for measure-based learning. The overall analysis of the research shows that measure-based learning is a promising area of research with potential for further exploration. We suggest directions for future research that might help realize measure-based neural networks.The study is an investigation on the feasibility of using a generic inductive bias for backpropagation artificial neural networks, which could incorporate any one or a combination of problem specific performance metrics to be optimized. We have identified several limitations of both the standard error backpropagation mechanism as well the inherent gradient search approach. These limitations suggest exploration of methods other than backpropagation, as well use of global search methods instead of gradient search. Also, we emphasize the importance of taking the representational bias of the neural network in consideration, since only a combination of both procedural and representational bias can provide highly optimal solutions.
7
Rimer, Michael Edwin. "Improving Neural Network Classification Training." Diss., CLICK HERE for online access, 2007. http://contentdm.lib.byu.edu/ETD/image/etd2094.pdf.
Full text
8
Singh, Y., and M. Mars. "A pilot study to integrate HIV drug resistance gold standard interpretation algorithms using neural networks." Journal for New Generation Sciences, Vol 11, Issue 2: Central University of Technology, Free State, Bloemfontein, 2013. http://hdl.handle.net/11462/639.
Full textAbstract:
Published ArticleThere are several HIV drug resistant interpretation algorithms which produce different resistance measures even if applied to the same resistance profile. This discrepancy leads to confusion in the mind of the physician when choosing the best ARV therapy.
9
Ncube, Israel. "Stochastic approximation of artificial neural network-type learning algorithms, a dynamical systems approach." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2001. http://www.collectionscanada.ca/obj/s4/f2/dsk3/ftp04/NQ60559.pdf.
Full text
10
Topalli, Ayca Kumluca. "Hybrid Learning Algorithm For Intelligent Short-term Load Forecasting." Phd thesis, METU, 2003. http://etd.lib.metu.edu.tr/upload/627505/index.pdf.
Full textAbstract:
Short-term load forecasting (STLF) is an important part of the power generation
process. For years, it has been achieved by traditional approaches stochastic like
time seriesbut, new methods based on artificial intelligence emerged recently in literature and started to replace the old ones in the industry. In order to follow the latest developments and to have a modern system, it is aimed to make a research on STLF in Turkey, by neural networks. For this purpose, a method is proposed to forecast Turkey&rsquo
s total electric load one day in advance. A hybrid learning scheme that combines off-line learning with real-time forecasting is developed to make use of the available past data for adapting the weights and to further adjust these connections according to the changing conditions. It is also suggested to tune the step size iteratively for better accuracy. Since a single neural network model cannot cover all load types, data are clustered due to the differences in their characteristics. Apart from this, special days are extracted from the normal training sets and handled separately. In this way, a solution is proposed for all load types, including working days, weekends and special holidays. For the selection of input parameters, a technique based on principal component analysis is suggested. A traditional ARMA model is constructed for the same data as a benchmark and results are compared. Proposed method gives lower percent errors all the time, especially for holiday loads. The average error for year 2002 data is obtained as 1.60%.
11
Mailah, Musa. "Intelligent active force control of a rigid robot arm using neural network and iterative learning algorithms." Thesis, University of Dundee, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.269529.
Full text
12
Reiling, Anthony J. "Convolutional Neural Network Optimization Using Genetic Algorithms." University of Dayton / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1512662981172387.
Full text
13
Wikström, Johan. "Evaluating supervised machine learning algorithms to predict recreational fishing success : A multiple species, multiple algorithms approach." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-172995.
Full textAbstract:
This report examines three different machine learning algorithms and their effectiveness for predicting recreational fishing success. Recreational fishing is a huge pastime but reliable methods of predicting fishing success have largely been missing. This report compares random forest, linear regression and multilayer perceptron to a reasonable baseline model for predicting fishing success. Fishing success is defined as the expected weight of the fish caught. Previous reports have mainly focused on commercial fishing or limited the research to examining the impact of a single variable. In this exploratory study, multiple attributes and multiple algorithms are examined to determine if supervised machine learning is a viable tool to predict recreational fishing success. Recreational fishing success can potentially be predicted by a large number of attributes, which may be different for different species. In this report, data is fetched from multiple sources and combined into a unified data format. The primary source of data is a database from the fishing app FishBrain, containing data of over 250000 logged catches. Another is the World Weather Online API which supplies weather data. The report focuses on the four most common species in the database, largemouth bass, Micropterus salmoides, northern pike, Esox lucius, rainbow trout, Oncorhynchus mykiss and European perch, Perca fluviatilis with a focus on largemouth bass since it has the most data available. Algorithms are evaluated using the Weka data mining software. Hyperparameters are found using cross-validation and some data is used as a test set to validate the results after cross-validation. Results are measured as the error compared to a baseline algorithm. Random forest is the most effective algorithm in the experiments, reducing error compared to the baseline for all the examined fish species. It is also found that no single variable affects the chosen metric of fishing success much, but rather a combination of most of the examined variables is needed to give optimal predictions. In conclusion, the random forest algorithm can be used to predict fishing success across multiple species. It performs significantly better than linear regression, multilayer perceptron and the baseline on crossvalidation and on the testing set.I denna rapport evalueras tre olika maskininlärningsalgoritmer och deras effektivitet för att förutsäga framgång inom sportfiske. Sport- fiske är en mycket populär hobby, men pålitliga metoder att förutsäga framgångsrikt sportfiske saknas. Denna rapport jämför random forest, linjär regression och flerlagers neurala nätverk mot en rimlig baselinealgorithm för att förutsäga framgång inom sportfiske. Framgång defineras som fiskens förväntade vikt i kg. Tidigare undersökningar har huvudsakligen fokuserat på kommersiellt fiske eller begränsat undersökningen till påverkan av en enskild variabel. I denna studie undersöks flera attribut och algoritmer för att avgöra om övervakad maskininlärning är ett användbart verktyg för att förutsäga framgång inom sportfiske. Framgång inom sportfiske kan potentiellt påverkas av ett stort antal attribut som kan vara olika för olika arter. I denna studie hämtas data från ett flertal källor som kombineras i ett unifierat dataformat. Den primära datakällan är en databas tillhörande sportfiskeappen FishBrain som innehåller över 250000 loggade fångster. En annan källa är World Weather Online:s API som bidrar med väderdata. Rapporten fokuserar på de fyra vanligaste arterna i databasen, largemouth bass, Micropterus salmoides, gädda, Esox lucius, regnbågsöring, Oncorhynchus mykiss och europeisk abborre, Perca fluviatilis med ett särskilt fokus på largemouth bass eftersom den har mest data tillgängligt. Algoritmerna evalueras med hjälp av data mining-verktyget Weka. Hyperparametrar bestäms med hjälp av korsvalidering och en delmängd av datan separeras och används för att validera resultaten efter korsvalidering. Resultaten mäts relativt en baseline-algoritm. Random forest är den mest effektiva algoritmen i experimenten och reducerar felet jämfört med baseline-algoritmen för alla undersökta fiskarter. Inget enskilt attribut påverkar slutresultatet mycket utan det behövs en kombination av flera attribut för att ge optimala prediktioner. Slutsatsen blir att random forest kan användas för att förutsäga framgång inom sportfiske för flera olika fiskarter. Den presterar signifikant bättre än linjär regression, flerlagers neuralt nätverk och baselinealgoritmen på korsvalidering och på testdelmängden.
14
Apprey-Hermann, Joseph Kwame. "Evaluating The Predictability of Pseudo-Random Number Generators Using Supervised Machine Learning Algorithms." Youngstown State University / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=ysu1588805461290138.
Full text
15
Chisholm, David. "Implementation of Multivariate Artificial Neural Networks Coupled With Genetic Algorithms for the Multi-Objective Property Prediction and Optimization of Emulsion Polymers." DigitalCommons@CalPoly, 2019. https://digitalcommons.calpoly.edu/theses/2045.
Full textAbstract:
Machine learning has been gaining popularity over the past few decades as computers have become more advanced. On a fundamental level, machine learning consists of the use of computerized statistical methods to analyze data and discover trends that may not have been obvious or otherwise observable previously. These trends can then be used to make predictions on new data and explore entirely new design spaces. Methods vary from simple linear regression to highly complex neural networks, but the end goal is similar. The application of these methods to material property prediction and new material discovery has been of high interest as many researchers have begun using the structure-property relationships of materials in conjunction with computational modeling to discover new materials with novel chemical and physical properties.
One such class of materials is that of emulsion polymers, which are heavily used in the coatings industry as they serve as the binder in many waterborne coating systems. The great advantage of these materials is that they are synthesized in water at high solids (30-70%) and therefore are largely compliant with stringent environmental regulations. The chemistry of these polymers is highly variant, but the predominant chemistries include copolymers of styrene and acrylic monomers such as n-butyl acrylate or copolymers of only acrylic monomers. Due to the high degree of complexity and variability of these systems, modeling their behavior according to structure-property relationships is currently impractical. Instead, this thesis will demonstrate the use of supervised machine learning methods in conjunction with genetic algorithms to predict and optimize emulsion polymer performance based on recipe composition. These emulsion polymers will also be evaluated for use in concrete coatings meant to be applied with minimal preparation work, i.e. no etching.
16
Mohammadisohrabi, Ali. "Design and implementation of a Recurrent Neural Network for Remaining Useful Life prediction." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2020.
Find full textAbstract:
A key idea underlying many Predictive Maintenance solutions is Remaining Useful Life (RUL) of machine parts, and it simply involves a prediction on the time remaining before a machine part is likely to require repair or replacement. Nowadays, with respect to fact that the systems are getting more complex, the innovative Machine Learning and Deep Learning algorithms can be deployed to study the more sophisticated correlations in complex systems. The exponential increase in both data accumulation and processing power make the Deep Learning algorithms more desirable that before. In this paper a Long Short-Term Memory (LSTM) which is a Recurrent Neural Network is designed to predict the Remaining Useful Life (RUL) of Turbofan Engines. The dataset is taken from NASA data repository. Finally, the performance obtained by RNN is compared to the best Machine Learning algorithm for the dataset.
17
Malmgren, Henrik. "Revision of an artificial neural network enabling industrial sorting." Thesis, Uppsala universitet, Institutionen för teknikvetenskaper, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-392690.
Full textAbstract:
Convolutional artificial neural networks can be applied for image-based object classification to inform automated actions, such as handling of objects on a production line. The present thesis describes theoretical background for creating a classifier and explores the effects of introducing a set of relatively recent techniques to an existing ensemble of classifiers in use for an industrial sorting system.The findings indicate that it's important to use spatial variety dropout regularization for high resolution image inputs, and use an optimizer configuration with good convergence properties. The findings also demonstrate examples of ensemble classifiers being effectively consolidated into unified models using the distillation technique. An analogue arrangement with optimization against multiple output targets, incorporating additional information, showed accuracy gains comparable to ensembling. For use of the classifier on test data with statistics different than those of the dataset, results indicate that augmentation of the input data during classifier creation helps performance, but would, in the current case, likely need to be guided by information about the distribution shift to have sufficiently positive impact to enable a practical application. I suggest, for future development, updated architectures, automated hyperparameter search and leveraging the bountiful unlabeled data potentially available from production lines.
18
Granström, Daria, and Johan Abrahamsson. "Loan Default Prediction using Supervised Machine Learning Algorithms." Thesis, KTH, Matematisk statistik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-252312.
Full textAbstract:
It is essential for a bank to estimate the credit risk it carries and the magnitude of exposure it has in case of non-performing customers. Estimation of this kind of risk has been done by statistical methods through decades and with respect to recent development in the field of machine learning, there has been an interest in investigating if machine learning techniques can perform better quantification of the risk. The aim of this thesis is to examine which method from a chosen set of machine learning techniques exhibits the best performance in default prediction with regards to chosen model evaluation parameters. The investigated techniques were Logistic Regression, Random Forest, Decision Tree, AdaBoost, XGBoost, Artificial Neural Network and Support Vector Machine. An oversampling technique called SMOTE was implemented in order to treat the imbalance between classes for the response variable. The results showed that XGBoost without implementation of SMOTE obtained the best result with respect to the chosen model evaluation metric.Det är nödvändigt för en bank att ha en bra uppskattning på hur stor risk den bär med avseende på kunders fallissemang. Olika statistiska metoder har använts för att estimera denna risk, men med den nuvarande utvecklingen inom maskininlärningsområdet har det väckt ett intesse att utforska om maskininlärningsmetoder kan förbättra kvaliteten på riskuppskattningen. Syftet med denna avhandling är att undersöka vilken metod av de implementerade maskininlärningsmetoderna presterar bäst för modellering av fallissemangprediktion med avseende på valda modelvaldieringsparametrar. De implementerade metoderna var Logistisk Regression, Random Forest, Decision Tree, AdaBoost, XGBoost, Artificiella neurala nätverk och Stödvektormaskin. En översamplingsteknik, SMOTE, användes för att behandla obalansen i klassfördelningen för svarsvariabeln. Resultatet blev följande: XGBoost utan implementering av SMOTE visade bäst resultat med avseende på den valda metriken.
19
Johansson, David. "Price Prediction of Vinyl Records Using Machine Learning Algorithms." Thesis, Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-96464.
Full textAbstract:
Machine learning algorithms have been used for price prediction within several application areas. Examples include real estate, the stock market, tourist accommodation, electricity, art, cryptocurrencies, and fine wine. Common approaches in studies are to evaluate the accuracy of predictions and compare different algorithms, such as Linear Regression or Neural Networks. There is a thriving global second-hand market for vinyl records, but the research of price prediction within the area is very limited. The purpose of this project was to expand on existing knowledge within price prediction in general to evaluate some aspects of price prediction of vinyl records. That included investigating the possible level of accuracy and comparing the efficiency of algorithms. A dataset of 37000 samples of vinyl records was created with data from the Discogs website, and multiple machine learning algorithms were utilized in a controlled experiment. Among the conclusions drawn from the results was that the Random Forest algorithm generally generated the strongest results, that results can vary substantially between different artists or genres, and that a large part of the predictions had a good accuracy level, but that a relatively small amount of large errors had a considerable effect on the general results.
20
Duncan, Andrew Paul. "The analysis and application of artificial neural networks for early warning systems in hydrology and the environment." Thesis, University of Exeter, 2014. http://hdl.handle.net/10871/17569.
Full textAbstract:
Artificial Neural Networks (ANNs) have been comprehensively researched, both from a computer scientific perspective and with regard to their use for predictive modelling in a wide variety of applications including hydrology and the environment. Yet their adoption for live, real-time systems remains on the whole sporadic and experimental. A plausible hypothesis is that this may be at least in part due to their treatment heretofore as “black boxes” that implicitly contain something that is unknown, or even unknowable. It is understandable that many of those responsible for delivering Early Warning Systems (EWS) might not wish to take the risk of implementing solutions perceived as containing unknown elements, despite the computational advantages that ANNs offer. This thesis therefore builds on existing efforts to open the box and develop tools and techniques that visualise, analyse and use ANN weights and biases especially from the viewpoint of neural pathways from inputs to outputs of feedforward networks. In so doing, it aims to demonstrate novel approaches to self-improving predictive model construction for both regression and classification problems. This includes Neural Pathway Strength Feature Selection (NPSFS), which uses ensembles of ANNs trained on differing subsets of data and analysis of the learnt weights to infer degrees of relevance of the input features and so build simplified models with reduced input feature sets. Case studies are carried out for prediction of flooding at multiple nodes in urban drainage networks located in three urban catchments in the UK, which demonstrate rapid, accurate prediction of flooding both for regression and classification. Predictive skill is shown to reduce beyond the time of concentration of each sewer node, when actual rainfall is used as input to the models. Further case studies model and predict statutory bacteria count exceedances for bathing water quality compliance at 5 beaches in Southwest England. An illustrative case study using a forest fires dataset from the UCI machine learning repository is also included. Results from these model ensembles generally exhibit improved performance, when compared with single ANN models. Also ensembles with reduced input feature sets, using NPSFS, demonstrate as good or improved performance when compared with the full feature set models. Conclusions are drawn about a new set of tools and techniques, including NPSFS and visualisation techniques for inspection of ANN weights, the adoption of which it is hoped may lead to improved confidence in the use of ANN for live real-time EWS applications.
21
Wilson, Dennis G. "Évolution des principes de la conception des réseaux de neurones artificiels." Thesis, Toulouse 3, 2019. http://www.theses.fr/2019TOU30075.
Full textAbstract:
Le cerveau biologique est composé d'un ensemble d'éléments qui évoluent depuis des millions d'années. Les neurones et autres cellules forment un réseau complexe d'interactions duquel émerge l'intelligence. Bon nombre de concepts neuronaux provenant de l’étude du cerveau biologique ont été utilisés dans des modèles informatiques pour développer les algorithmes d’intelligence artificielle. C'est particulièrement le cas des réseaux neuronaux profonds modernes qui révolutionnent actuellement de nombreux domaines de recherche en informatique tel que la vision par ordinateur, la traduction automatique, le traitement du langage naturel et bien d'autres. Cependant, les réseaux de neurones artificiels ne sont basés que sur un petit sous-ensemble de fonctionnalités biologiques du cerveau. Ils se concentrent souvent sur les fonctions globales, homogènes et à un système complexe et localement hétérogène. Dans cette thèse, nous avons d'examiner le cerveau biologique, des neurones simples aux réseaux capables d'apprendre. Nous avons examiné individuellement la cellule neuronale, la formation des connexions entre les cellules et comment un réseau apprend au fil du temps. Pour chaque composant, nous avons utilisé l'évolution artificielle pour trouver les principes de conception neuronale qui nous avons optimisés pour les réseaux neuronaux artificiels. Nous proposons aussi un modèle fonctionnel du cerveau qui peut être utilisé pour étudier plus en profondeur certains composants du cerveau, incluant toutes les fonctions conçues pour l'optimisation automatique telles que l'évolution. Notre objectif est d'améliorer la performance des réseaux de neurones artificiels par les moyens inspirés des neurosciences modernes. Cependant, en évaluant les effets biologiques dans le contexte d'un agent virtuel, nous espérons également fournir des modèles de cerveau utiles aux biologistesThe biological brain is an ensemble of individual components which have evolved over millions of years. Neurons and other cells interact in a complex network from which intelligence emerges. Many of the neural designs found in the biological brain have been used in computational models to power artificial intelligence, with modern deep neural networks spurring a revolution in computer vision, machine translation, natural language processing, and many more domains. However, artificial neural networks are based on only a small subset of biological functionality of the brain, and often focus on global, homogeneous changes to a system that is complex and locally heterogeneous. In this work, we examine the biological brain, from single neurons to networks capable of learning. We examine individually the neural cell, the formation of connections between cells, and how a network learns over time. For each component, we use artificial evolution to find the principles of neural design that are optimized for artificial neural networks. We then propose a functional model of the brain which can be used to further study select components of the brain, with all functions designed for automatic optimization such as evolution. Our goal, ultimately, is to improve the performance of artificial neural networks through inspiration from modern neuroscience. However, through evaluating the biological brain in the context of an artificial agent, we hope to also provide models of the brain which can serve biologists
22
Salem, Tawfiq. "Learning to Map the Visual and Auditory World." UKnowledge, 2019. https://uknowledge.uky.edu/cs_etds/86.
Full textAbstract:
The appearance of the world varies dramatically not only from place to place but also from hour to hour and month to month. Billions of images that capture this complex relationship are uploaded to social-media websites every day and often are associated with precise time and location metadata. This rich source of data can be beneficial to improve our understanding of the globe. In this work, we propose a general framework that uses these publicly available images for constructing dense maps of different ground-level attributes from overhead imagery. In particular, we use well-defined probabilistic models and a weakly-supervised, multi-task training strategy to provide an estimate of the expected visual and auditory ground-level attributes consisting of the type of scenes, objects, and sounds a person can experience at a location. Through a large-scale evaluation on real data, we show that our learned models can be used for applications including mapping, image localization, image retrieval, and metadata verification.
23
Price, Ryan William. "Hierarchical Temporal Memory Cortical Learning Algorithm for Pattern Recognition on Multi-core Architectures." PDXScholar, 2011. https://pdxscholar.library.pdx.edu/open_access_etds/202.
Full textAbstract:
Strongly inspired by an understanding of mammalian cortical structure and function, the Hierarchical Temporal Memory Cortical Learning Algorithm (HTM CLA) is a promising new approach to problems of recognition and inference in space and time. Only a subset of the theoretical framework of this algorithm has been studied, but it is already clear that there is a need for more information about the performance of HTM CLA with real data and the associated computational costs. For the work presented here, a complete implementation of Numenta's current algorithm was done in C++. In validating the implementation, first and higher order sequence learning was briefly examined, as was algorithm behavior with noisy data doing simple pattern recognition. A pattern recognition task was created using sequences of handwritten digits and performance analysis of the sequential implementation was performed. The analysis indicates that the resulting rapid increase in computing load may impact algorithm scalability, which may, in turn, be an obstacle to widespread adoption of the algorithm. Two critical hotspots in the sequential code were identified and a parallelized version was developed using OpenMP multi-threading. Scalability analysis of the parallel implementation was performed on a state of the art multi-core computing platform. Modest speedup was readily achieved with straightforward parallelization. Parallelization on multi-core systems is an attractive choice for moderate sized applications, but significantly larger ones are likely to remain infeasible without more specialized hardware acceleration accompanied by optimizations to the algorithm.
24
Caetano, Marcelo Freitas. "Sintese sonora auto-organizavel atraves da aplicação de algoritmos bio-inspirados." [s.n.], 2006. http://repositorio.unicamp.br/jspui/handle/REPOSIP/261756.
Full textAbstract:
Orientadores: Fernando Jose Von Zuben, Jonatas ManzolliDissertação (mestrado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação
Made available in DSpace on 2018-08-06T18:10:14Z (GMT). No. of bitstreams: 1 Caetano_MarceloFreitas_M.pdf: 11758987 bytes, checksum: 2521dc99ef68d0b0a4e06b9ea4751fc5 (MD5) Previous issue date: 2006
Resumo: Não há limitações teóricas para o uso do computador como fonte de sons musicais. O computador digital permite a produção de qualquer som concebivel dada a seqüência correta de números (amostras digitais). No entanto, produzir uma dada seqüência de números que corresponda a um som musical que possua determinadas características perceptivas desejadas é uma tarefa de difícil resolução. Grande parte dos métodos e sistemas de síntese sonora digital utiliza modelos e/ou incorpora técnicas que não levam em conta a natureza dinâmica dos sons musicais ou que não foram originalmente desenvolvidas para manipulação musical. Neste trabalho, é apresentada uma abordagem populacional para síntese sonora no domínio temporal. Foi estudado um espaço sonoro e um conjunto de atratores, isto é, um conjunto de formas de onda com qualidades sonoras desejadas e definidas a priori, e foi possível obter sons que possuem características associadas a um ou mais atratores, representando variantes dos mesmos. Este método de síntese de sons musicais pode ser interpretado como um processo de busca no espaço vetorial que contém todas as possibilidades sonoras decorrentes da representação adotada, e tem por objetivo a criação de formas de onda digítalizadas com características emergentes e potencial para serem utilizadas em diversas aplicações musicais. Os resultados representam variantes e/ou possuem íntersecções das características próprias dos atratores, responsáveis por indicar as regiões de interesse do espaço de busca. A proposta de pesquisa envolveu a utilização de algoritmos bioinspirados - os quais expressam propriedades de sistemas auto-organizados e adaptativos - como definidores de processos de geração e estruturação dos elementos sonoros, entendidos aqui como problemas de otimização. A auto-organização e os mecanismos de manutenção de diversidade e de adaptação, intrínsecos aos sistemas bio-inspirados, fundamentam a proposta no sentido de viabilizarem a emergência temporal de estruturas estáveis sem um elemento organizador externo
Abstract: There are no theoretical limitations to the use of the computer as a source of musical sounds. The digital computer allows for the production of any conceivable sound given the carrect sequence af numbers (digital samples). Nevertheless, producing the correct sequence of numbers that correspond to a musical sound expressing predefined perceptual characteristics is a very difficult task. Most sound synthesis methods and systems utilize models and/or incorporate techniques which do not take into account the dynamic nature of musical sounds or were not originally developed for the manipulation of musical tones. In this work we are proposing a populational sound synthesis approach in the time domain. A soundspace and a set of attractors, i.e. waveforms containing a priari desired features or qualities, and a population of agents communicating by means of local interaction were studied, and it was possible to attain sounds which share some qualities from more than one of the attractors, resulting exclusively from low-Ievel rules followed by these agents. This sound synthesis method can be regarded as a search in the vector space that contains ali the possible sounds resulting from the adopted representation, and its objective is to synthesize digital waveforms that possess emergent properties and the potential to be used in musical applications. The resulting sounds are variants or hybrids that share some of the intrinsic features of the attractors, which are responsible for indicating the regions of interest in the search space. This proposal involved the use of bio-inspired algorithms, which express features of adaptive, self-organizing systems, as definers of generating and structuring processes of sound elements, regarded herein as optimization processes. Self-organization and diversity maintenance and adaptation mechanisms, intrinsic to bio-inspired systems, lay the foundations of this proposal so as to make viable the temporal emergence of stable structures without an externa I organizing element
Mestrado
Engenharia de Computação
Mestre em Engenharia Elétrica
25
Melo, Davyd Bandeira de. "Algoritmos de aprendizagem para aproximaÃÃo da cinemÃtica inversa de robÃs manipuladores: um estudo comparativo." Universidade Federal do CearÃ, 2015. http://www.teses.ufc.br/tde_busca/arquivo.php?codArquivo=16997.
Full textAbstract:
In this dissertation it is reported the results of a comprehensive comparative study involving seven machine learning algorithms applied to the task of approximating the inverse kinematic model of 3 robotic arms (planar, PUMA 560 and Motoman HP6). The evaluated algorithm are the following ones: Multilayer Perceptron (MLP), Extreme
Learning Machine (ELM), Least Squares Support Vector Regression (LS-SVR), Minimal Learning Machine (MLM), Gaussian Processes (GP), Adaptive Network-Based Fuzzy
Inference Systems (ANFIS) and Local Linear Mapping (LLM). Each algorithm is evaluated with respect to its accuracy in estimating the joint angles given the cartesian coordinates which comprise end-effector trajectories within the robot workspace. A comprehensive evaluation of the performances of the aforementioned algorithms is carried out based on correlation analysis of the residuals. Finally, hypothesis testing procedures are also executed in order to verifying if there are significant differences in performance among the best algorithms.Nesta dissertaÃÃo sÃo reportados os resultados de um amplo estudo comparativo envolvendo sete algoritmos de aprendizado de mÃquinas aplicados à tarefa de aproximaÃÃo do modelo cinemÃtico inverso de 3 robÃs manipuladores (planar, PUMA 560 e Motoman HP6). Os algoritmos avaliados sÃo os seguintes: Perceptron Multicamadas (MLP), MÃquina de Aprendizado Extremo (ELM), RegressÃo de MÃnimos Quadrados via Vetores-Suporte (LS-SVR), MÃquina de Aprendizado MÃnimo (MLM), Processos Gaussianos (PG), Sistema de InferÃncia Fuzzy Baseado em Rede Adaptativa (ANFIS) e Mapeamento Linear Local (LLM). Estes algoritmos sÃo avaliados quanto à acurÃcia na estimaÃÃo dos Ãngulos das juntas dos robÃs manipuladores em experimentos envolvendo a geraÃÃo de vÃrios tipos de trajetÃrias no volume de trabalho dos referidos robÃs. Uma avaliaÃÃo abrangente do desempenho de cada algoritmo à feito com base na anÃlise dos resÃduos e testes de hipÃteses sÃo executados para verificar se hà diferenÃas significativas entre os desempenhos dos melhores algoritmos.
26
Milaré, Claudia Regina. ""Extração de conhecimento de redes neurais artificiais utilizando sistemas de aprendizado simbólico e algoritmos genéticos"." Universidade de São Paulo, 2003. http://www.teses.usp.br/teses/disponiveis/55/55134/tde-11082004-004358/.
Full textAbstract:
Em Aprendizado de Máquina - AM não existe um único algoritmo que é sempre melhor para todos os domínios de aplicação. Na prática, diversas pesquisas mostram que Redes Neurais Artificiais - RNAs têm um 'bias' indutivo apropriado para diversos domínios. Em razão disso, RNAs têm sido aplicadas na resolução de vários problemas com desempenho satisfatório. Sistemas de AM simbólico possuem um 'bias' indutivo menos flexível do que as RNAs. Enquanto que as RNAs são capazes de aprender qualquer função, sistemas de AM simbólico geralmente aprendem conceitos que podem ser descritos na forma de hiperplanos. Por outro lado, sistemas de AM simbólico representam o conceito induzido por meio de estruturas simbólicas, as quais são geralmente compreensíveis pelos seres humanos. Assim, sistemas de AM simbólico são preferíveis quando é essencial a compreensibilidade do conceito induzido. RNAs carecem da capacidade de explicar suas decisões, uma vez que o conhecimento é codificado na forma de valores de seus pesos e 'thresholds'. Essa codificação é difícil de ser interpretada por seres humanos. Em diversos domínios de aplicação, tal como aprovação de crédito e diagnóstico médico, prover uma explicação sobre a classificação dada a um determinado caso é de crucial importância. De um modo similar, diversos usuários de sistemas de AM simbólico desejam validar o conhecimento induzido, com o objetivo de assegurar que a generalização feita pelo algoritmo é correta. Para que RNAs sejam aplicadas em um maior número de domínios, diversos pesquisadores têm proposto métodos para extrair conhecimento compreensível de RNAs. As principais contribuições desta tese são dois métodos que extraem conhecimento simbólico de RNAs. Os métodos propostos possuem diversas vantagens sobre outros métodos propostos previamente, tal como ser aplicáveis a qualquer arquitetura ou algoritmo de aprendizado de RNAs supervisionadas. O primeiro método proposto utiliza sistemas de AM simbólico para extrair conhecimento de RNAs, e o segundo método proposto estende o primeiro, combinado o conhecimento induzido por diversos sistemas de AM simbólico por meio de um Algoritmo Genético - AG. Os métodos propostos são analisados experimentalmente em diversos domínios de aplicação. Ambos os métodos são capazes de extrair conhecimento simbólico com alta fidelidade em relação à RNA treinada. Os métodos propostos são comparados com o método TREPAN, apresentando resultados promissores. TREPAN é um método bastante conhecido para extrair conhecimento de RNAs.In Machine Learning - ML there is not a single algorithm that is the best for all application domains. In practice, several research works have shown that Artificial Neural Networks - ANNs have an appropriate inductive bias for several domains. Thus, ANNs have been applied to a number of data sets with high predictive accuracy. Symbolic ML algorithms have a less flexible inductive bias than ANNs. While ANNs can learn any input-output mapping, i.e., ANNs have the universal approximation property, symbolic ML algorithms frequently learn concepts describing them using hyperplanes. On the other hand, symbolic algorithms are needed when a good understating of the decision process is essential, since symbolic ML algorithms express the knowledge induced using symbolic structures that can be interpreted and understood by humans. ANNs lack the capability of explaining their decisions since the knowledge is encoded as real-valued weights and biases of the network. This encoding is difficult to be interpreted by humans. In several application domains, such as credit approval and medical diagnosis, providing an explanation related to the classification given to a certain case is of crucial importance. In a similar way, several users of ML algorithms desire to validate the knowledge induced, in order to assure that the generalization made by the algorithm is correct. In order to apply ANNs to a larger number of application domains, several researches have proposed methods to extract comprehensible knowledge from ANNs. The primary contribution of this thesis consists of two methods that extract symbolic knowledge, expressed as decision rules, from ANNs. The proposed methods have several advantages over previous methods, such as being applicable to any architecture and supervised learning algorithm of ANNs. The first method uses standard symbolic ML algorithm to extract knowledge from ANNs, and the second method extends the first method by combining the knowledge induced by several symbolic ML algorithms through the application of a Genetic Algorithm - GA. The proposed methods are experimentally analyzed in a number of application domains. Results show that both methods are capable to extract symbolic knowledge having high fidelity with trained ANNs. The proposed methods are compared with TREPAN, showing promising results. TREPAN is a well known method to extract knowledge from ANNs.
27
Heinen, Milton Roberto. "Controle inteligente do caminhar de robôs móveis simulados." Universidade do Vale do Rio do Sinos, 2007. http://www.repositorio.jesuita.org.br/handle/UNISINOS/2243.
Full textAbstract:
Made available in DSpace on 2015-03-05T13:58:27Z (GMT). No. of bitstreams: 0
Previous issue date: 10Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
O objetivo desta dissertação é propor, testar e avaliar o uso de técnicas de Aprendizado de Máquina (ML) na configuração automática do controle do caminhar de robôs com pernas. Para que este objetivo fosse atingido, um extensa pesquisa de técnicas do estado da arte foi realizada e descrita neste trabalho. Esta pesquisa permitiu a elaboração do modelo proposto, chamado de LegGen, que foi implementado em um protótipo. O protótipo modelo em questão permite a utilização de vários tipos de robôs, compostos de quatro, seis ou mais patas, e além disto permite a evolução da morfologia dos robôs. Utilizando o protótipo, é possível a realização de experimentos com robôs autônomos dotados de pernas, em um ambiente virtual tridimensional realístico, através de simulações baseadas em física. Foi utilizada a biblioteca ODE (Open Dynamics Engine) para a simulação de corpos rígidos e articulações, permitindo assim simular forças agindo nas articulações (atuadores), gravidade e colisões, entre outras propriedades físicas dos
The main goal of this dissertation is to propose, to test and to evaluate the use of Machine Learning (ML) techniques in the automatic con_guration of the gait control in legged robots. In order to achieve this goal, an extensive research about state-of-the-art techniques was accomplished and they are described in this work. This research allowed the development of the proposed model, called LegGen, which was implemented in a prototype. The proposed model allows the use of several different robot models with four, six or more paws. Besides that, the prototype allows also to study the robot's morphology evolution. The implemented prototype allows to accomplish experiments with autonomous legged robots, in a realistic three-dimensional virtual environment, through physics based simulations. The ODE (Open Dynamics Engine) software library was used in the physical simulation of rigid bodies and articulations, allowing to simulate forces acting in the articulations (actuators), gravity and collisions, among other
28
Elkin, Colin P. "Development of Adaptive Computational Algorithms for Manned and Unmanned Flight Safety." University of Toledo / OhioLINK, 2018. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1544640516618623.
Full text
29
Santos, Rosiane Correia. "LearnInPlanner: uma abordagem de aprendizado supervisionado com redes neurais para solução de problemas de planejamento clássico." Universidade de São Paulo, 2013. http://www.teses.usp.br/teses/disponiveis/100/100131/tde-25012014-115621/.
Full textAbstract:
A busca progressiva no espaço de estados é uma das abordagens mais populares de Planejamento Automatizado. O desempenho dos algoritmos de busca progressiva é influenciado pela heurística independente de domínio utilizada para guiá-lo. Nesse contexto, o foco do presente trabalho consiste em investigar técnicas de aprendizado de máquina supervisionadas que possibilitaram agregar à heurística do plano relaxado, comumente utilizada em abordagens atuais de planejamento, informações sobre o domínio em questão que viessem a ser úteis ao algoritmo de busca. Essas informações foram representadas por meio de um espaço de características do problema de planejamento e uma rede neural MLP foi aplicada para estimar uma nova função heurística para guiar a busca por meio de um processo de regressão não linear. Uma vez que o conjunto de características disponíveis para a construção da nova função heurística é grande, foi necessário a definição de um processo de seleção de características capaz de determinar qual conjunto de características de entrada da rede resultaria em melhor desempenho para o modelo de regressão. Portanto, para a seleção de características, aplicou-se uma abordagem de algoritmos genéticos. Como principal resultado, tem-se uma análise comparativa do desempenho entre a utilização da heurística proposta neste trabalho e a utilização da heurística do plano relaxado para guiar o algoritmo de busca na tarefa de planejamento. Para a análise empírica foram utilizados domínios de diferentes complexidades disponibilizados pela Competições Internacionais de Planejamento. Além dos resultados empíricos e análises comparativas, as contribuições deste trabalho envolvem o desenvolvimento de um novo planejador independente de domínio, denominado LearnInPlanner. Esse planejador utiliza a nova função heurística estimada por meio do processo de aprendizado e o algoritmo de Busca Gulosa para solucionar os problemas de planejamento.The forward state-space search is one of the most popular Automated Planning approaches. The performance of forward search algorithms is affected by the domain-independent heuristic being used. In this context, the focus of this work consisted on investigating techniques of supervised machine learning that make possible to agregate to the relaxed plan heuristic, commonly used in current planning approaches, information about the domain which could be useful to the search algorithm. This information has been represented through a feature space of planning problem and a MLP neural network has been applied to estimate a new heuristic function for guiding the search through a non-linear regression process. Once the set of features available for the construction of the new heuristic function is large, it was necessary to define a feature selection process capable of determining which set of neural network input features would result in the best performance for the regression model. Therefore, for selecting features, an approach of genetic algorithms has been applied. As the main result, one has obtained a comparative performance analysis between the use of heuristic proposed in this work and the use of the relaxed plan heuristic to guide the search algorithm in the planning task. For the empirical analysis were used domains with different complexities provided by the International Planning Competitions. In addition to the empirical results and comparative analysis, the contributions of this work involves the development of a new domain-independent planner, named LearnInPlanner. This planner uses the new heuristic function estimated by the learning process and the Greedy Best-First search algorithm to solve planning problems.
30
Russo, Nicholas A. "DiSH: Democracy in State Houses." DigitalCommons@CalPoly, 2019. https://digitalcommons.calpoly.edu/theses/1967.
Full textAbstract:
In our current political climate, state level legislators have become increasingly impor- tant. Due to cuts in funding and growing focus at the national level, public oversight for these legislators has drastically decreased. This makes it difficult for citizens and activists to understand the relationships and commonalities between legislators. This thesis provides three contributions to address this issue. First, we created a data set containing over 1200 features focused on a legislator’s activity on bills. Second, we created embeddings that represented a legislator’s level of activity and engagement for a given bill using a custom model called Democracy2Vec. Third, we provided a case study focused on the 2015-2016 California State Legislator and had our results verified by a political expert. Our results show that our embeddings can explain relationships between legislator and how they will likely act during the legislative process.
31
Luna, Huamaní Ivette Raymunda 1978. "Analises de series temporais e modelagem baseada em regras nebulosas." [s.n.], 2007. http://repositorio.unicamp.br/jspui/handle/REPOSIP/261147.
Full textAbstract:
Orientadores: Secundino Soares Filho, Rosangela BalliniTese (doutorado) - Universidade Estadual de Campinas, Faculdade de Engenharia Eletrica e de Computação
Made available in DSpace on 2018-08-11T11:20:51Z (GMT). No. of bitstreams: 1 LunaHuamani_IvetteRaymunda_D.pdf: 1516017 bytes, checksum: 0b1789c54ac07dc411d69c82d77f8ac3 (MD5) Previous issue date: 2007
Resumo: Este trabalho propõe uma metodologia baseada em regras nebulosas para a modelagem e previsão de séries temporais. Inicialmente, os dados são pré-processados para, a seguir, ocorrer a seleção de variáveis que serão utilizadas pelos modelos de série temporal. Para essa finalidade, nesta tese propõe-se um conjunto de aproximações necessárias para o cálculo do critério de informação mútua parcial, o qual é a base para o algoritmo de seleção de entradas utilizado. A próxima etapa corresponde à determinação da estrutura do modelo e ajuste dos parâmetros. Com o intuito de definir de forma automática a estrutura do modelo, de forma simultânea ao ajuste dos parâmetros, dois algoritmos de aprendizado construtivo - offiine e online são propostos. Ambos os algoritmos utilizam como base para o seu desenvolvimento o algoritmo da maximização da verossimilhança, assim como critérios de geração e punição (ou poda) de regras nebulosas. Finalmente, o modelo obtido é validado e aplicado .na previsão de um e vários passos à frente. Análises comparativas são apresentadas utilizando séries temporais sintéticas e de problemas reais. Os resultados mostram que as propostas deste trabalho são uma alternativa eficiente para a modelagem e previsão de séries temporais
Abstract: This work presents a methodology for time series modeling and forecasting. First, the methodology considers the data pre-processing and the system identification, which implies on the selection of a suitable set of input variables for modeling the time series. In order to achieve this task, this work proposes an algorithm for input selection and a set of approximations that are necessary for estimating the partia! mutual information criterion, which is the base of the algorithm used at this stage. Then, the mo deI is built and adjusted. With the aim of performing an automatic structure selection and parameters adjustment simultaneously, this thesis proposes two constructive learning algorithms, namely ofRine and online. These algorithms are based on the Expectation Maximization optimization technique, as well as on adding and pruning operators of fuzzy rules that are also proposed in this work. Finally, models are validated and applied to one-step ahead and multi-step ahead forecasting. Comparative analysis using synthetic and real time series are detailed. The results show the adequate performance of the proposed approach and presents it as a promising alternative for time series modeling and forecasting
Doutorado
Energia Eletrica
Doutor em Engenharia Elétrica
32
Susnjak, Teo. "Accelerating classifier training using AdaBoost within cascades of boosted ensembles : a thesis presented in partial fulfillment of the requirements for the degree of Master of Science in Computer Sciences at Massey University, Auckland, New Zealand." Massey University, 2009. http://hdl.handle.net/10179/1002.
Full textAbstract:
This thesis seeks to address current problems encountered when training classifiers within the framework of cascades of boosted ensembles (CoBE). At present, a signifi- cant challenge facing this framework are inordinate classifier training runtimes. In some cases, it can take days or weeks (Viola and Jones, 2004; Verschae et al., 2008) to train a classifier. The protracted training runtimes are an obstacle to the wider use of this framework (Brubaker et al., 2006). They also hinder the process of producing effective object detection applications and make the testing of new theories and algorithms, as well as verifications of others research, a considerable challenge (McCane and Novins, 2003). An additional shortcoming of the CoBE framework is its limited ability to train clas- sifiers incrementally. Presently, the most reliable method of integrating new dataset in- formation into an existing classifier, is to re-train a classifier from beginning using the combined new and old datasets. This process is inefficient. It lacks scalability and dis- cards valuable information learned in previous training. To deal with these challenges, this thesis extends on the research by Barczak et al. (2008), and presents alternative CoBE frameworks for training classifiers. The alterna- tive frameworks reduce training runtimes by an order of magnitude over common CoBE frameworks and introduce additional tractability to the process. They achieve this, while preserving the generalization ability of their classifiers. This research also introduces a new framework for incrementally training CoBE clas- sifiers and shows how this can be done without re-training classifiers from beginning. However, the incremental framework for CoBEs has some limitations. Although it is able to improve the positive detection rates of existing classifiers, currently it is unable to lower their false detection rates.
33
Hauschild, Jennifer M. "Fourier transform ion cyclotron resonance mass spectrometry for petroleomics." Thesis, University of Oxford, 2012. http://ora.ox.ac.uk/objects/uuid:8604a373-fb6b-4bc0-8dc1-464a191b1fac.
Full textAbstract:
The past two decades have witnessed tremendous advances in the field of high accuracy, high mass resolution data acquisition of complex samples such as crude oils and the human proteome. With the development of Fourier transform ion cyclotron resonance mass spectrometry, the rapidly growing field of petroleomics has emerged, whose goal is to process and analyse the large volumes of complex and often poorly understood data on crude oils generated by mass spectrometry. As global oil resources deplete, oil companies are increasingly moving towards the extraction and refining of the still plentiful reserves of heavy, carbon rich and highly contaminated crude oil. It is essential that the oil industry gather the maximum possible amount of information about the crude oil prior to setting up the drilling infrastructure, in order to reduce processing costs. This project describes how machine learning can be used as a novel way to extract critical information from complex mass spectra which will aid in the processing of crude oils. The thesis discusses the experimental methods involved in acquiring high accuracy mass spectral data for a large and key industry-standard set of crude oil samples. These data are subsequently analysed to identify possible links between the raw mass spectra and certain physical properties of the oils, such as pour point and sulphur content. Methods including artificial neural networks and self organising maps are described and the use of spectral clustering and pattern recognition to classify crude oils is investigated. The main focus of the research, the creation of an original simulated annealing genetic algorithm hybrid technique (SAGA), is discussed in detail and the successes of modelling a number of different datasets using all described methods are outlined. Despite the complexity of the underlying mass spectrometry data, which reflects the considerable chemical diversity of the samples themselves, the results show that physical properties can be modelled with varying degrees of success. When modelling pour point temperatures, the artificial neural network achieved an average prediction error of less than 10% while SAGA predicted the same values with an average accuracy of more than 85%. It did not prove possible to model any of the other properties with such statistical significance; however improvements to feature extraction and pre-processing of the spectral data as well as enhancement of the modelling techniques should yield more consistent and statistically reliable results. These should in due course lead to a comprehensive model which the oil industry can use to process crude oil data using rapid and cost effective analytical methods.
34
Atiya, Amir Abu-Mostafa Yaser S. "Learning algorithms for neural networks /." Diss., Pasadena, Calif. : California Institute of Technology, 1991. http://resolver.caltech.edu/CaltechETD:etd-09232005-083502.
Full text
35
Muthuraman, Sethuraman. "The evolution of modular artificial neural networks." Thesis, Robert Gordon University, 2005. http://hdl.handle.net/10059/284.
Full textAbstract:
This thesis describes a novel approach to the evolution of Modular Artificial Neural Networks. Standard Evolutionary Algorithms, used in this application include: Genetic Algorithms, Evolutionary Strategies, Evolutionary Programming and Genetic Programming; however, these often fail in the evolution of complex systems, particularly when such systems involve multi-domain sensory information which interacts in complex ways with system outputs. The aim in this work is to produce an evolutionary method that allows the structure of the network to evolve from simple to complex as it interacts with a dynamic environment. This new algorithm is therefore based on Incremental Evolution. A simulated model of a legged robot was used as a test-bed for the approach. The algorithm starts with a simple robotic body plan. This then grows incrementally in complexity along with its controlling neural network and the environment it reacts with. The network grows by adding modules to its structure - so the technique may also be termed a Growth Algorithm. Experiments are presented showing the successful evolution of multi-legged gaits and a simple vision system. These are then integrated together to form a complete robotic system. The possibility of the evolution of complex systems is one advantage of the algorithm and it is argued that it represents a possible path towards more advanced artificial intelligence. Applications in Electronics, Computer Science, Mechanical Engineering and Aerospace are also discussed.
36
Hook, Jaroslav. "Are artificial neural networks learning machines?" Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1998. http://www.collectionscanada.ca/obj/s4/f2/dsk2/ftp01/MQ38651.pdf.
Full text
37
Hadjifaradji, Saeed. "Learning algorithms for restricted neural networks." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 2000. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape3/PQDD_0016/NQ48102.pdf.
Full text
38
Krundel, Ludovic. "On microelectronic self-learning cognitive chip systems." Thesis, Loughborough University, 2016. https://dspace.lboro.ac.uk/2134/21804.
Full textAbstract:
After a brief review of machine learning techniques and applications, this Ph.D. thesis examines several approaches for implementing machine learning architectures and algorithms into hardware within our laboratory. From this interdisciplinary background support, we have motivations for novel approaches that we intend to follow as an objective of innovative hardware implementations of dynamically self-reconfigurable logic for enhanced self-adaptive, self-(re)organizing and eventually self-assembling machine learning systems, while developing this new particular area of research. And after reviewing some relevant background of robotic control methods followed by most recent advanced cognitive controllers, this Ph.D. thesis suggests that amongst many well-known ways of designing operational technologies, the design methodologies of those leading-edge high-tech devices such as cognitive chips that may well lead to intelligent machines exhibiting conscious phenomena should crucially be restricted to extremely well defined constraints. Roboticists also need those as specifications to help decide upfront on otherwise infinitely free hardware/software design details. In addition and most importantly, we propose these specifications as methodological guidelines tightly related to ethics and the nowadays well-identified workings of the human body and of its psyche.
39
Kostka, Filip. "Umělá neuronová síť pro modelování polí uvnitř automobilu." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2014. http://www.nusl.cz/ntk/nusl-220578.
Full textAbstract:
The project deals with artificial neural networks. After designing and debugging the test data set and the training sample set, we created a multilayer perceptron network in the Neural NetworkToolbox (NNT) of Matlab. When creating networks, we used different training algorithms and algorithms improving the generalization of the network. When creating a radial basis network, we did not use the NNT, but a specific source code in Matlab was written. Functionality of neural networks was tested on simple training and testing patterns. Realistic training data were obtained by the simulation of twelve monoconic antennas operating in the frequency range from 2 to 6 GHz. Antennas were located inside a mathematical model of Octavia II. Using CST simulations, electromagnetic fields in a car were obtained. Trained networks are described by regressive characteristics andthe mean square error of training. Algorithms improving generalization are applied on the created and trained networks. The performance of individual networks is mutually compared.
40
Frøyen, Even Bruvik. "Exploring Learning in Evolutionary Artificial Neural Networks." Thesis, Norges teknisk-naturvitenskapelige universitet, Institutt for datateknikk og informasjonsvitenskap, 2011. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-15689.
Full textAbstract:
Evolutionary artificial neural networks can adapt to new circumstances, and handle slight changes without catastrophic failure. However, under constantly changing circumstances, resulting in unpredictable grounds for evaluating success, the lack of memory of previous adaptations are a limiting factor. While further evolution can allow adaptations to new changes, the same is required for a return to a previous environment. To reduce the need for further evolution to deal with previously seen problems, this thesis looks at an approach to encourage previous knowledge to be retained across generations. It does this using back propagation in conjunction with an implementation of the HyperNEAT neuroevolutionary algorithm.
41
Ferguson, Alistair. "Learning in RAM-based artificial neural networks." Thesis, University of Hertfordshire, 1995. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.283866.
Full text
42
Tay, Leng Phuan. "Fast learning artificial neural networks for classification." Thesis, Loughborough University, 1994. https://dspace.lboro.ac.uk/2134/25161.
Full textAbstract:
Neural network applications can generally be divided into two categories. The first involves function approximation, where the neural network is trained to perform intelligent interpolation and curve fitting from the training data. The second category involves classification, where specific exemplar classes are used to train the neural network. This thesis directs its investigations towards the latter, i.e. classification. Most existing neural network models are developments that arise directly from human cognition research. It is felt that while neural network research should head towards the development of models that resemble the cognitive system of the brain, researchers should not abandon the search for useful task oriented neural networks. These may not possess the intricacies of human cognition, but are efficient in solving industrial classification tasks. It is the objective of this thesis to develop a neural network that is fast learning, able to generalise and achieve good capacity to discern different patterns even though some patterns may be similar in structure. This eventual neural network will be used in the pattern classification environment. The first model developed, was the result of studying and modifying the basic ART I model. The "Fast Learning Artificial Neural Network I" (FLANN I) maintains good generalisation properties and is progressive in learning. Although this neural network achieves fast learning speeds of one epoch, it was limited only to binary inputs and was unable to operate on continuous values. This posed a real problem because industrial applications usually require the manipulation of continuous values. The second model, FLANN II, was designed based on the principles of FLANN I. It was built on the nearest neighbour recall principle, which allowed the network to operate On continuous values. Experiments were conducted on the two models designed and the results were favourable. FLANN II was able to learn the points in a single epoch and obtain exceptional accuracy. This is a significant improvement to other researcher's results. A further study was conducted on the FLANN models in the parallel processing environment. The parallel investigations led to the development of a new paradigm; Parallel Distributed Neural Networks (PDNNs), which allows several neural networks to operate concurrently to solve a single classification problem. This paradigm is powerful because it is able to reduce the overall memory requirements for some classification problems.
43
Golea, Mostefa. "On efficient learning algorithms for neural networks." Thesis, University of Ottawa (Canada), 1993. http://hdl.handle.net/10393/6508.
Full textAbstract:
Inductive Inference Learning can be described in terms of finding a good approximation to some unknown classification rule f, based on a pre-classified set of training examples $\langle$x,f(x)$\rangle.$ One particular class of learning systems that has attracted much attention recently is the class of neural networks. But despite the excitement generated by neural networks, learning in these systems has proven to be a difficult task. In this thesis, we investigate different ways and means to overcome the difficulty of training feedforward neural networks. Our goal is to come up with efficient learning algorithms for new classes (or architectures) of neural nets. In the first approach, we relax the constraint of fixed architecture adopted by most neural learning algorithms. We describe two constructive learning algorithms for two-layer and tree-like networks. In the second approach, we adopt the "probably approximately correct" (PAC) learning model and we look for positive learnability results by restricting the distribution generating the training examples, the connectivity of the networks, and/or the weight values. This enables us to identify new classes of neural networks that are efficiently learnable in the chosen setting. In the third and final approach, we look at the problem of learning in neural networks from the average case point of view. In particular, we investigate the average case behavior of the well known clipped Hebb rule when learning different neural networks with binary weights. The arguments given for the "efficient learnability" range from extensive simulations to rigorous mathematical proofs.
44
Gadde, Pramod. "AFFINE IMAGE REGISTRATION USING ARTIFICIAL NEURAL NETWORKS." DigitalCommons@CalPoly, 2013. https://digitalcommons.calpoly.edu/theses/982.
Full textAbstract:
This thesis deals with image registration of MRI images using neural networks. Image registration combines multiple images of the same subject that were taken at different points in time, from different sensors, or from different points of views into a single image and coordinate system. Image registration is widely used in medical imaging and remote sensing. In this thesis feed forward neural networks and wavelet neural networks are used to estimate the parameters of registration. Simulations show that the wavelet networks provide significantly more accurate results than feed forward networks and other proposed methods including genetic algorithms. Both methods are also shown to be robust to noise and changes in parameter ranges.
45
Andersen, Mats Grønning. "Reservoir Production Optimization Using Genetic Algorithms and Artificial Neural Networks." Thesis, Norwegian University of Science and Technology, Department of Computer and Information Science, 2009. http://urn.kb.se/resolve?urn=urn:nbn:no:ntnu:diva-9985.
Full textAbstract:
This master's thesis has investigated how methods from artificial intelligence (AI) can be used to perform and augment production optimization of sub-sea oil reservoirs. The methods involved in this work are genetic algorithms (GAs) and artificial neural networks (ANNs). Different optimization schemes were developed by the author to perform production optimization on oil reservoir simulator models. The optimization involves finding good input parameter values for certain properties of the model, relating to how the wells in the oil reservoir operate. The research involves straightforward optimization using GAs, model approximations using ANNs, and also more advanced schemes using these methods together with other available technology to perform and augment reservoir optimization. With this work, the author has attempted to make a genuine contribution to all the research areas this master's thesis has touched upon, ranging from computer science and AI to process and petroleum engineering. The methods and approaches developed through this research were compared to the performance of each other and also to other approaches and methods used on the same challenges. The comparison found some of the developed optimization schemes to be very successful, while others were found to be less appropriate for solving the problem at hand. Some of the less successful approaches still showed considerable promise for simpler problems, leading the author to conclude that the developed schemes are suited for solving optimization problems in the petroleum industry.
46
侯江濤 and Kong-to William Hau. "Artificial neural networks, motor programs and motor learning." Thesis, The University of Hong Kong (Pokfulam, Hong Kong), 1999. http://hub.hku.hk/bib/B31240227.
Full text
47
Hau, Kong-to William. "Artificial neural networks, motor programs and motor learning /." Hong Kong : University of Hong Kong, 1999. http://sunzi.lib.hku.hk/hkuto/record.jsp?B2177920X.
Full text
48
Tavanaei, Amirhossein. "Spiking Neural Networks and Sparse Deep Learning." Thesis, University of Louisiana at Lafayette, 2019. http://pqdtopen.proquest.com/#viewpdf?dispub=10807940.
Full textAbstract:
This document proposes new methods for training multi-layer and deep spiking neural networks (SNNs), specifically, spiking convolutional neural networks (CNNs). Training a multi-layer spiking network poses difficulties because the output spikes do not have derivatives and the commonly used backpropagation method for non-spiking networks is not easily applied. Our methods use novel versions of the brain-like, local learning rule named spike-timing-dependent plasticity (STDP) that incorporates supervised and unsupervised components. Our method starts with conventional learning methods and converts them to spatio-temporally local rules suited for SNNs.
The training uses two components for unsupervised feature extraction and supervised classification. The first component refers to new STDP rules for spike-based representation learning that trains convolutional filters and initial representations. The second introduces new STDP-based supervised learning rules for spike pattern classification via an approximation to gradient descent by combining the STDP and anti-STDP rules. Specifically, the STDP-based supervised learning model approximates gradient descent by using temporally local STDP rules. Stacking these components implements a novel sparse, spiking deep learning model. Our spiking deep learning model is categorized as a variation of spiking CNNs of integrate-and-fire (IF) neurons with performance comparable with the state-of-the-art deep SNNs. The experimental results show the success of the proposed model for image classification. Our network architecture is the only spiking CNN which provides bio-inspired STDP rules in a hierarchy of feature extraction and classification in an entirely spike-based framework.
49
Bean, Ralph. "Vibrational control of chaos in artificial neural networks /." Online version of thesis, 2009. http://hdl.handle.net/1850/10645.
Full text
50
Lind, Benjamin. "Artificial Neural Networks for Image Improvement." Thesis, Linköpings universitet, Datorseende, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-137661.
Full textAbstract:
After a digital photo has been taken by a camera, it can be manipulated to be more appealing. Two ways of doing that are to reduce noise and to increase the saturation. With time and skills in an image manipulating program, this is usually done by hand. In this thesis, automatic image improvement based on artificial neural networks is explored and evaluated qualitatively and quantitatively. A new approach, which builds on an existing method for colorizing gray scale images is presented and its performance compared both to simpler methods and the state of the art in image denoising. Saturation is lowered and noise added to original images, which the methods receive as inputs to improve upon. The new method is shown to improve in some cases but not all, depending on the image and how it was modified before given to the method.