To see the other types of publications on this topic, follow the link: Neural networks (Computer science) Statistical mechanics.
Dissertations / Theses on the topic 'Neural networks (Computer science) Statistical mechanics'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 40 dissertations / theses for your research on the topic 'Neural networks (Computer science) Statistical mechanics.'
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
Whyte, William John. "Statistical mechanics of neural networks." Thesis, University of Oxford, 1995. http://ora.ox.ac.uk/objects/uuid:e17f9b27-58ac-41ad-8722-cfab75139d9a.
Full textAbstract:
We investigate five different problems in the field of the statistical mechanics of neural networks. The first three problems involve attractor neural networks that optimise particular cost functions for storage of static memories as attractors of the neural dynamics. We study the effects of replica symmetry breaking (RSB) and attempt to find algorithms that will produce the optimal network if error-free storage is impossible. For the Gardner-Derrida network we show that full RSB is necessary for an exact solution everywhere above saturation. We also show that, no matter what the cost function that is optimised, if the distribution of stabilities has a gap then the Parisi replica ansatz that has been made is unstable. For the noise-optimal network we find a continuous transition to replica symmetry breaking at the AT line, in line with previous studies of RSB for different networks. The change to RSBl improves the agreement between "experimental" and theoretical calculations of the local stability distribution ρ(λ) significantly. The effect on observables is smaller. We show that if the network is presented with a training set which has been generated from a set of prototypes by some noisy rule, but neither the noise level nor the prototypes are known, then the perceptron algorithm is the best initial choice to produce a network that will generalise well. If additional information is available more sophisticated algorithms will be faster and give a smaller generalisation error. The remaining problems deal with attractor neural networks with separable interaction matrices which can be used (under parallel dynamics) to store sequences of patterns without the need for time delays. We look at the effects of correlations on a singlesequence network, and numerically investigate the storage capacity of a network storing an extensive number of patterns in such sequences. When correlations are implemented along with a term in the interaction matrix designed to suppress some of the effects of those correlations, the competition between the two produces a rich range of behaviour. Contrary to expectations, increasing the correlations and the operating temperature proves capable of improving the sequenceprocessing behaviour of the network. Finally, we demonstrate that a network storing a large number of sequences of patterns using a Hebb-like rule can store approximately twice as many patterns as the network trained with the Hebb rule to store individual patterns.
2
Morabito, David L. "Statistical mechanics of neural networks and combinatorial opimization problems /." Online version of thesis, 1991. http://hdl.handle.net/1850/11089.
Full text
3
Chavali, Krishna Kumar. "Integration of statistical and neural network method for data analysis." Morgantown, W. Va. : [West Virginia University Libraries], 2006. https://eidr.wvu.edu/etd/documentdata.eTD?documentid=4749.
Full textAbstract:
Thesis (M.S.)--West Virginia University, 2006.Title from document title page. Document formatted into pages; contains viii, 68 p. : ill. (some col.). Includes abstract. Includes bibliographical references (p. 50-51).
4
Ramachandran, Sowmya. "Theory refinement of Bayesian networks with hidden variables /." Digital version accessible at:, 1998. http://wwwlib.umi.com/cr/utexas/main.
Full text
5
Mitchell, David. "Classification by Neural Network and Statistical Models in Tandem: Does Integration Enhance Performance?" Thesis, University of North Texas, 1998. https://digital.library.unt.edu/ark:/67531/metadc278874/.
Full textAbstract:
The major purposes of the current research are twofold. The first purpose is to present a composite approach to the general classification problem by using outputs from various parametric statistical procedures and neural networks. The second purpose is to compare several parametric and neural network models on a transportation planning related classification problem and five simulated classification problems.
6
Nortje, Willem Daniel. "Comparison of Bayesian learning and conjugate gradient descent training of neural networks." Pretoria : [s.n.], 2001. http://upetd.up.ac.za/thesis/available/etd-11092004-091241.
Full text
7
Abu-Rahmeh, Osama. "A statistical mechanics approach for an effective, scalable, and reliable distributed load balancing scheme for grid networks." Thesis, Liverpool John Moores University, 2009. http://researchonline.ljmu.ac.uk/5903/.
Full textAbstract:
The advances in computer and networking technologies over the past decades produced new type of collaborative computing environment called Grid Networks. Grid network is a parallel and distributed computing network system that possesses the ability to achieve a higher computing throughput by taking advantage of many computing resources available in the network. To achieve a scalable and reliable Grid network system, the workload needs to be efficiently distributed among the resources accessible on the network. A novel distributed algorithm based on statistical mechanics that provides an efficient load-balancing paradigm without any centralised monitoring is proposed here. The resulting load-balancer would be integrated into Grid network to increase its efficiency and resources utilisation. This distributed and scalable load-balancing framework is conducted using the biased random sampling (BRS) algorithm. In this thesis, a novel statistical mechanics approach that gives a distributed loadbalancing scheme by generating almost regular networks is proposed. The generated network system is self-organised and depends only on local information for load distribution and resource discovery. The in-degree of each node refers to its free resources, and job assignment and resource updating processes required for load balancing are accomplished by using random sampling (RS). An analytical solution for the stationary degree distributions has been derived that confirms that the edge distribution of the proposed network system is compatible with ER random networks. Therefore, the generated network system can provide an effective loadbalancing paradigm for the distributed resources accessible on large-scale network 1 systems. Furthermore, it has been demonstrated that introducing a geographic awareness factor in the random walk sampling can reduce the effects of communication latency in the Grid network environment. Theoretical and simulation results prove that the proposed BRS load-balancing scheme provides an effective, scalable, and reliable distributed load-balancing scheme for the distributed resources available on Grid networks.
8
Riggelsen, Carsten. "Approximation methods for efficient learning of Bayesian networks /." Amsterdam ; Washington, DC : IOS Press, 2008. http://www.loc.gov/catdir/toc/fy0804/2007942192.html.
Full text
9
Kapur, Loveena. "Investigation of artificial neural networks, alternating conditional expectation, and Bayesian methods for reservoir characterization /." Digital version accessible at:, 1998. http://wwwlib.umi.com/cr/utexas/main.
Full text
10
Suermondt, Henri Jacques. "Explanation in Bayesian belief networks." Full text available online (restricted access), 1992. http://images.lib.monash.edu.au/ts/theses/suermondt.pdf.
Full text
11
Menke, Joshua E. "Improving machine learning through oracle learning /." Diss., CLICK HERE for online access, 2007. http://contentdm.lib.byu.edu/ETD/image/etd1726.pdf.
Full text
12
Winn, David. "An analysis of neural networks and time series techniques for demand forecasting." Thesis, Rhodes University, 2007. http://hdl.handle.net/10962/d1004362.
Full textAbstract:
This research examines the plausibility of developing demand forecasting techniques which are consistently and accurately able to predict demand. Time Series Techniques and Artificial Neural Networks are both investigated. Deodorant sales in South Africa are specifically studied in this thesis. Marketing techniques which are used to influence consumer buyer behaviour are considered, and these factors are integrated into the forecasting models wherever possible. The results of this research suggest that Artificial Neural Networks can be developed which consistently outperform industry forecasting targets as well as Time Series forecasts, suggesting that producers could reduce costs by adopting this more effective method.
13
Tang, Adelina Lai Toh. "Application of the tree augmented naive Bayes network to classification and forecasting /." [St. Lucia, Qld.], 2004. http://www.library.uq.edu.au/pdfserve.php?image=thesisabs/absthe.pdf.
Full text
14
Myers, James William. "Stochastic algorithms for learning with incomplete data an application to Bayesian networks /." Full text available online (restricted access), 1999. http://images.lib.monash.edu.au/ts/theses/Myers.pdf.
Full text
15
Phadke, Amit Ashok. "Predicting open-source software quality using statistical and machine learning techniques." Master's thesis, Mississippi State : Mississippi State University, 2004. http://library.msstate.edu/etd/show.asp?etd=etd-11092004-105801.
Full text
16
Krishnamurthy, Raju Chemical Sciences & Engineering Faculty of Engineering UNSW. "Prediction of consumer liking from trained sensory panel information: evaluation of artificial neural networks (ANN)." Awarded by:University of New South Wales. Chemical Sciences & Engineering, 2007. http://handle.unsw.edu.au/1959.4/40746.
Full textAbstract:
This study set out to establish artificial neural networks (ANN) as an alternate to regression methods (multiple linear, principal components and partial least squares regression) to predict consumer liking from trained sensory panel data. The study has two parts viz., I) Flavour study - evaluation of ANNs to predict consumer flavour preferences from trained sensory panel data and 2) Fragrance study ??? evaluation of different ANN architectures to predict consumer fragrance liking from trained sensory panel data. In this study, a multi-layer feedforward neural network architecture with input, hidden and output layer(s) was designed. The back-propagation algorithm was utilised in training of neural networks. The network learning parameters such as learning rate and momentum rate were optimised by the grid experiments for a fixed number of learning cycles. In flavour study, ANNs were trained using the trained sensory panel raw data as well as transformed data. The networks trained with sensory panel raw data achieved 98% correct learning, whereas the testing was within the range of 28 -35%. A suitable transformation methods were applied to reduce the variations in trained sensory panel raw data. The networks trained with transformed sensory panel data achieved between 80-90% correct learning and 80-95% correct testing. In fragrance study, ANNs were trained using the trained sensory panel raw data as well as principal component data. The networks trained with sensory panel raw data achieved 100% correct learning, and testing was in a range of 70-94%. Principal component analysis was applied to reduce redundancy in the trained sensory panel data. The networks trained with principal component data achieved about 100% correct learning and 90% correct testing. It was shown that due to its excellent noise tolerance property and ability to predict more than one type of consumer liking using a single model, the ANN approach promises to be an effective modelling tool.
17
Le, Hai Son. "Continuous space models with neural networks in natural language processing." Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00776704.
Full textAbstract:
The purpose of language models is in general to capture and to model regularities of language, thereby capturing morphological, syntactical and distributional properties of word sequences in a given language. They play an important role in many successful applications of Natural Language Processing, such as Automatic Speech Recognition, Machine Translation and Information Extraction. The most successful approaches to date are based on n-gram assumption and the adjustment of statistics from the training data by applying smoothing and back-off techniques, notably Kneser-Ney technique, introduced twenty years ago. In this way, language models predict a word based on its n-1 previous words. In spite of their prevalence, conventional n-gram based language models still suffer from several limitations that could be intuitively overcome by consulting human expert knowledge. One critical limitation is that, ignoring all linguistic properties, they treat each word as one discrete symbol with no relation with the others. Another point is that, even with a huge amount of data, the data sparsity issue always has an important impact, so the optimal value of n in the n-gram assumption is often 4 or 5 which is insufficient in practice. This kind of model is constructed based on the count of n-grams in training data. Therefore, the pertinence of these models is conditioned only on the characteristics of the training text (its quantity, its representation of the content in terms of theme, date). Recently, one of the most successful attempts that tries to directly learn word similarities is to use distributed word representations in language modeling, where distributionally words, which have semantic and syntactic similarities, are expected to be represented as neighbors in a continuous space. These representations and the associated objective function (the likelihood of the training data) are jointly learned using a multi-layer neural network architecture. In this way, word similarities are learned automatically. This approach has shown significant and consistent improvements when applied to automatic speech recognition and statistical machine translation tasks. A major difficulty with the continuous space neural network based approach remains the computational burden, which does not scale well to the massive corpora that are nowadays available. For this reason, the first contribution of this dissertation is the definition of a neural architecture based on a tree representation of the output vocabulary, namely Structured OUtput Layer (SOUL), which makes them well suited for large scale frameworks. The SOUL model combines the neural network approach with the class-based approach. It achieves significant improvements on both state-of-the-art large scale automatic speech recognition and statistical machine translations tasks. The second contribution is to provide several insightful analyses on their performances, their pros and cons, their induced word space representation. Finally, the third contribution is the successful adoption of the continuous space neural network into a machine translation framework. New translation models are proposed and reported to achieve significant improvements over state-of-the-art baseline systems.
18
Ribeiro, Fabiano. "Sensor inteligente em fibra ótica para localização de deformações em estruturas planas." Universidade Tecnológica Federal do Paraná, 2014. http://repositorio.utfpr.edu.br/jspui/handle/1/836.
Full textAbstract:
CAPES, CNPq, FINEP, Fundação AraucáriaNeste trabalho é apresentado um estudo sobre a aplicabilidade de redes de Bragg na análise de impactos em estruturas planas. Para tanto, os dispositivos foram caracterizados, preliminarmente, quanto à deformação mecânica e temperatura. Nesta abordagem, para a validação experimental, quatro redes de Bragg foram fixadas nos cantos de uma placa de polimetilmetacrilato que, posteriormente, foi submetida a impactos mecânicos. Os efeitos de impactos produzidos na placa foram detectados pelas redes de Bragg, sendo que suas respostas em λ ao longo de 0,3 segundos foram utilizadas para treinar e testar redes neurais artificiais do tipo perceptron multicamadas. As localizações dos impactos nos quadrantes foram, então, fornecidas pela rede neural artificial, a qual demonstrou que a localização pode ser prevista com uma taca de classificação correta de aproximadamente 90% na etapa de validação. Outra RNA foi implementada para localizar coordenadas de posições de impacto, a qual permitiu fazer uma análise quantitativa dos erros, realizando uma comparação do valor desejado e o valor de saída da RNA na localização de um impacto em um plano. O maior erro médio (Em) em relação ao valor alvo foi de 0,401 cm em x, e 0,703 cm em relação à y, sendo que, o maior desvio padrão (σEm) foi de 0,896 cm em x, e 1,572 cm em y considerando cinco diferentes posições de impacto na etapa de teste de RNA.
In this work the applicability of fiber Bragg grantings as tools for the analysis of impacts on planar structures was studied. In a first step, Bragg grantings were characterized and their thermal and strain sensitivities were determined. The experiments were carried out with four fiber Bragg gratings. Being that their responses in λ along 0.3 second were used to train and test a multilayer perceptron artificial neural network. The locations of impacts in quadrants were supplied by the artificial neural network. The results demonstrate that such location can be predicted with correct classification rate of approximately 90.0% in validation step. Another RNA was implemented to locate impact coordinates, wich allowed a quantitative analysis of errors by performing a comparison of the desired value and the output value provided by the RNA on the location of an impact on a plan. The largest mean error (Em) to the target value was 0,401 cm for the coordinate x and 0,703 cm for y, considering five different points of impact in the test step.
19
Almér, Henrik. "Machine learning and statistical analysis in fuel consumption prediction for heavy vehicles." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-172306.
Full textAbstract:
I investigate how to use machine learning to predict fuel consumption in heavy vehicles. I examine data from several different sources describing road, vehicle, driver and weather characteristics and I find a regression to a fuel consumption measured in liters per distance. The thesis is done for Scania and uses data sources available to Scania. I evaluate which machine learning methods are most successful, how data collection frequency affects the prediction and which features are most influential for fuel consumption. I find that a lower collection frequency of 10 minutes is preferable to a higher collection frequency of 1 minute. I also find that the evaluated models are comparable in their performance and that the most important features for fuel consumption are related to the road slope, vehicle speed and vehicle weight.Jag undersöker hur maskininlärning kan användas för att förutsäga bränsleförbrukning i tunga fordon. Jag undersöker data från flera olika källor som beskriver väg-, fordons-, förar- och väderkaraktäristiker. Det insamlade datat används för att hitta en regression till en bränsleförbrukning mätt i liter per sträcka. Studien utförs på uppdrag av Scania och jag använder mig av datakällor som är tillgängliga för Scania. Jag utvärderar vilka maskininlärningsmetoder som är bäst lämpade för problemet, hur insamlingsfrekvensen påverkar resultatet av förutsägelsen samt vilka attribut i datat som är mest inflytelserika för bränsleförbrukning. Jag finner att en lägre insamlingsfrekvens av 10 minuter är att föredra framför en högre frekvens av 1 minut. Jag finner även att de utvärderade modellerna ger likvärdiga resultat samt att de viktigaste attributen har att göra med vägens lutning, fordonets hastighet och fordonets vikt.
20
Hazarika, Subhashis. "Statistical and Machine Learning Approaches For Visualizing and Analyzing Large-Scale Simulation Data." The Ohio State University, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=osu1574692702479196.
Full text
21
Giacomossi, Luiz Carlos. "Método não invasivo utilizando acelerômetro para classificar movimentos normais e anormais de humanos." Universidade Tecnológica Federal do Paraná, 2011. http://repositorio.utfpr.edu.br/jspui/handle/1/913.
Full textAbstract:
O objetivo desta pesquisa é a captura, detecção e classificação de movimentos humanos anormais (tremores, vibrações, espasmos e contrações musculares) e movimentos normais do cotidiano. Um dispositivo não invasivo, desenvolvido pelos alunos de iniciação científica do CPGEI-UTFPR, baseado no componente integrado eletrônico acelerômetro, foi colocado no pulso de voluntários para a captura dos movimentos objetos de estudo. Todos os experimentos foram realizados no laboratório Biota da UTFPR. Os movimentos andando, correndo, aceno de tchau, batendo palmas e tremores foram capturados de 5 voluntários adultos. Um pré-processamento off-line é efetuado por um programa desenvolvido na linguagem Matlab 6.5, o qual extrai as principais características que devem refletir a amplitude, intensidade e frequência de cada movimento e fornecer um arquivo contendo os padrões supervisionados. Utilizou-se uma rede neural fuzzy do tipo FAN (Free Associative Neuron) e uma rede neural MLP (Multi-Layer Perceptron), para classificar um banco de dados contendo um total de 375 padrões, dos quais 250 padrões (50 de cada movimento) para a fase de treinamento e 125 padrões (25 de cada movimento) para a fase de validação dos dados. Os percentuais de acerto médio obtidos na classificação dos dados capturados de 5 indivíduos foram de 81,6% para a rede neural FAN e 72,6% para a rede MLP. Outro experimento foi realizado para capturar os mesmos movimentos do estudo anterior, provenientes de um único indivíduo. De um total de 2100 padrões, 1500 foram utilizados para treinamento (300 de cada movimento) e 600 padrões (120 de cada movimento) para a validação dos dados. Os percentuais de acerto médio na classificação dos dados foram de 98,2% para a rede neural FAN e 96,7% para a rede neural MLP observando-se uma melhora significativa nos resultados. Um último experimento foi realizado acrescentando ao banco de dados mais alguns movimentos executados por um único indivíduo: penteando, aparafusando, círculos, socos no ar e coçando a perna. Os percentuais de acerto médio obtidos na classificação dos dados foram de 99,3% para a rede neural FAN e 99,1% para a rede neural MLP. Os resultados da classificação dos dados para um total de 10 movimentos e padrões elaborados com 13 características foram obtidos baseando-se em um banco de dados contendo um total de 4200 padrões, dos quais 3000 padrões (300 de cada movimento) para a fase de treinamento e 1200 padrões (120 de cada movimento) para a fase de validação dos dados. Neste experimento houve uma melhora ainda mais significativa na classificação dos dados, tendo em vista o acréscimo de 3 novas características aos padrões de treinamento: valores posturais (offset) extraídos dos sinais referentes aos eixos x, y e z do acelerômetro.The aim of this research is the capture, detection and classification of abnormal human movements (tremors, vibrations, spasms and muscle contractions) and normal movements of everyday life. A non-invasive device, developed by undergraduate students of UTFPR, based on integrated electronic accelerometer, was placed on the wrist of volunteers to capture the movements. All experiments were performed in the laboratory Biota of CPGEI-UTFPR. The movement of walking, running, waving a goodbye, clapping and shaking, were captured in 5 adult volunteers. A pre-processing was done off-line by a program developed using Matlab 6.5, which extracts key features that should reflect the breadth, intensity and frequency of each movement and provide a file containing the standard supervised. We used a fuzzy neural network-type FAN (Free Associative Neuron) and a neural network MLP (Multi-Layer Perceptron) to classify a database containing a total of 375 patterns, of which 250 patterns (50 of each movement) for the training phase and 125 patterns (25 of each movement) to data validation. The average percentage of correct classification of data obtained from 5 individuals, were captured from 81.6% for the neural network FAN and 72.6% for MLP. Another experiment was conducted to capture the same movements in the previous study from a single individual. From a total of 2100 patterns, 1500 were used for training (300 for each movement) and 600 patterns (120 for each movement) for validation. The average percentage of correct classification of the data were 98.2% for the neural network FAN, 96.7% for MLP neural network, observing a significant improvement in the results. A final experiment was performed adding to the database some more movements performed by a single individual: combing, bolting, circles, punching the air and scratching his leg. The average percentage of correct classification of the data obtained were 99.3% for the neural network FAN and 99.1% for MLP neural network. The results of the classification of data for a total of 10 movements and elaborate patterns with 13 features were obtained based on a database containing a total of 4200 patterns, of which 3000 patterns (300 for each movement) for the training and 1200 patterns (120 for each movement) to data validation. In this experiment there was a further improvement in data classification, considering the addition of three new features to the training patterns, postural values (offset) extracted from the signals related to the axes x, y and z of the accelerometer.
22
Nam, Kyungdoo T. "A Heuristic Procedure for Specifying Parameters in Neural Network Models for Shewhart X-bar Control Chart Applications." Thesis, University of North Texas, 1993. https://digital.library.unt.edu/ark:/67531/metadc278815/.
Full textAbstract:
This study develops a heuristic procedure for specifying parameters for a neural network configuration (learning rate, momentum, and the number of neurons in a single hidden layer) in Shewhart X-bar control chart applications. Also, this study examines the replicability of the neural network solution when the neural network is retrained several times with different initial weights.
23
Vurkaç, Mehmet. "Prestructuring Multilayer Perceptrons based on Information-Theoretic Modeling of a Partido-Alto-based Grammar for Afro-Brazilian Music: Enhanced Generalization and Principles of Parsimony, including an Investigation of Statistical Paradigms." PDXScholar, 2011. https://pdxscholar.library.pdx.edu/open_access_etds/384.
Full textAbstract:
The present study shows that prestructuring based on domain knowledge leads to statistically significant generalization-performance improvement in artificial neural networks (NNs) of the multilayer perceptron (MLP) type, specifically in the case of a noisy real-world problem with numerous interacting variables. The prestructuring of MLPs based on knowledge of the structure of a problem domain has previously been shown to improve generalization performance. However, the problem domains for those demonstrations suffered from significant shortcomings: 1) They were purely logical problems, and 2) they contained small numbers of variables in comparison to most data-mining applications today. Two implications of the former were a) the underlying structure of the problem was completely known to the network designer by virtue of having been conceived for the problem at hand, and b) noise was not a significant concern in contrast with real-world conditions. As for the size of the problem, neither computational resources nor mathematical modeling techniques were advanced enough to handle complex relationships among more than a few variables until recently, so such problems were left out of the mainstream of prestructuring investigations. In the present work, domain knowledge is built into the solution through Reconstructability Analysis, a form of information-theoretic modeling, which is used to identify mathematical models that can be transformed into a graphic representation of the problem domain's underlying structure. Employing the latter as a pattern allows the researcher to prestructure the MLP, for instance, by disallowing certain connections in the network. Prestructuring reduces the set of all possible maps (SAPM) that are realizable by the NN. The reduced SAPM--according to the Lendaris-Stanley conjecture, conditional probability, and Occam's razor--enables better generalization performance than with a fully connected MLP that has learned the same I/O mapping to the same extent. In addition to showing statistically significant improvement over the generalization performance of fully connected networks, the prestructured networks in the present study also compared favorably to both the performance of qualified human agents and the generalization rates in classification through Reconstructability Analysis alone, which serves as the alternative algorithm for comparison.
24
Setia, Ronald. "Modeling and Diagnosis of Excimer Laser Ablation." Diss., Georgia Institute of Technology, 2005. http://hdl.handle.net/1853/7634.
Full textAbstract:
Recent advances in the miniaturization, functionality, and integration of integrated circuits and packages, such as the system-on-package (SOP) methodology, require increasing use of microvias that generates vertical signal paths in a high-density multilayer substrate. A scanning projection excimer laser system has been utilized to fabricate the microvias. In this thesis, a novel technique implementing statistical experimental design and neural networks (NNs) is used to characterize and model the excimer laser ablation process for microvia formation. Vias with diameters from 10 50 micrometer have been ablated in DuPont Kapton(r) E polyimide using an Anvik HexScan(tm) 2150 SXE pulsed excimer laser operating at 308 nm. Accurate NN models, developed from experimental data, are obtained for microvia responses, including ablated thickness, via diameter, wall angle, and resistance. Subsequent to modeling, NNs and genetic algorithms (GAs) are utilized to generate optimal process recipes for the laser tool. Such recipes can be used to produce desired microvia responses, including open vias, specific diameter, steep wall angle, and low resistance. With continuing advancement in the use of excimer laser systems in microsystems packaging has come an increasing need to offset capital equipment investment and lower equipment downtime. In this thesis, an automated in-line failure diagnosis system using NNs and Dempster-Shafer (D-S) theory is implemented. For the sake of comparison, an adaptive neuro-fuzzy approach is applied to achieve the same objective. Both the D-S theory and neuro-fuzzy logic are used to develop an automated inference system to specifically identify failures. Successful results in failure detection and diagnosis are obtained from the two approaches. The result of this investigation will benefit both engineering and management. Engineers will benefit from high yield, reliable production, and low equipment down-time. Business people, on the other hand, will benefit from cost-savings resulting from more production-worthy (i.e., lower maintenance) laser ablation equipment.
25
Rombach, Michaela Puck. "Colouring, centrality and core-periphery structure in graphs." Thesis, University of Oxford, 2013. http://ora.ox.ac.uk/objects/uuid:7326ecc6-a447-474f-a03b-6ec244831ad4.
Full textAbstract:
Krivelevich and Patkós conjectured in 2009 that χ(G(n, p)) ∼ χ=(G(n, p)) ∼ χ∗=(G(n, p)) for C/n < p < 1 − ε, where ε > 0. We prove this conjecture for n−1+ε1 < p < 1 − ε2 where ε1, ε2 > 0. We investigate several measures that have been proposed to indicate centrality of nodes in networks, and find examples of networks where they fail to distinguish any of the vertices nodes from one another. We develop a new method to investigate core-periphery structure, which entails identifying densely-connected core nodes and sparsely-connected periphery nodes. Finally, we present an experiment and an analysis of empirical networks, functional human brain networks. We found that reconfiguration patterns of dynamic communities can be used to classify nodes into a stiff core, a flexible periphery, and a bulk. The separation between this stiff core and flexible periphery changes as a person learns a simple motor skill and, importantly, it is a good predictor of how successful the person is at learning the skill. This temporally defined core-periphery organisation corresponds well with the core- periphery detected by the method that we proposed earlier the static networks created by averaging over the subjects dynamic functional brain networks.
26
Ferreira, Eduardo Chaves. "Mineração de dados aplicados ao sistema integrado de administração financeira do governo federal - SIAFI : detecção de anomalias na emissão de notas de empenho." Laboratório Nacional de Computação Científica, 2008. http://www.lncc.br/tdmc/tde_busca/arquivo.php?codArquivo=163.
Full textAbstract:
Esta tese tem por objetivo propor um modelo para a detecção automática de indícios de irregularidades na execução da despesa pública, baseado em dados extraídos do Sistema Integrado de Administração Financeira do Governo Federal - SIAFI. O modelo proposto foi desenvolvido para atuar como ferramenta auxiliar ao trabalho de fiscalização da Administração Pública executado pelo Tribunal de Contas da União.
As análises realizadas pelo modelo baseiam-se em dois procedimentos complementares: sistema especialista e mineração de dados. A primeira alternativa permite criar um repositório de regras de conhecimento, extraídas da legislação e da experiência de analistas do TCU. A mineração de dados busca de forma automática informações não triviais, que não possam ser facilmente explicitadas através das regras de conhecimento.
A principal contribuição do trabalho é a sistematização do procedimento de detecção, detalhando os componentes do modelo e a interação entre eles. Com o objetivo de validar o modelo proposto, é feita a implementação do componente de mineração de dados, caracterizado no trabalho por um modelo matemático de comportamento quanto à execução da despesa e por algoritmos que, utilizando o modelo de comportamento, permitem detectar indícios de irregularidades. O componente de mineração de dados foi implementado com o uso de técnicas estatísticas, redes neurais e lógica nebulosa.In this work we propose a model to automatically detect irregularities in application of federal funds that may cause losses to the public treasury. The model uses data from the Sistema Integrado de Administração Financeira do Governo Federal - SIAFI. This model was created to help the Brazilian Court of Audit (TCU) in auditing the application of federal funds. The model has two modules, one is an expert system that will have the rules take form the legislation and from the experience of experts from TCU. The other module is a data mining module, that is composed by Behavior model and the detection part that uses Statistics techniques, Neural Networks and Fuzzy Logic to detect possible irregularities.
27
Mallet, Grégory. "Méthodes statistiques pour la prédiction de température dans les composants hyperfréquences." Phd thesis, INSA de Rouen, 2010. http://tel.archives-ouvertes.fr/tel-00586089.
Full textAbstract:
Cette thèse s'intéresse à l'application des méthodes d'apprentissage statistique pour la prédiction de température d'un composant électronique présent dans un radar. On étudie un cas simplifié des systèmes réels, le système étudié se limitant à un seul composant monté sur un système de refroidissement réduit. Le premier chapitre est consacré à la modélisation thermique. Après avoir présenté les principaux modes de transmission de l'agitation thermique, les modèles analytiques et numériques qui en découlent sont étudiés. En utilisant cette connaissance,le deuxième chapitre propose de choisir dans les méthodes de mesures les plus adaptées aux spécifications et aux contraintes de l'application choisie. Une fois que les bases de données ont été établies, nous pouvons utiliser dans le troisième chapitre les techniques de l'apprentissage statistique pour construire un modèle dynamique. Après un bref rappel sur les tenants et les aboutissants de la modélisation statistique, quatre familles de méthodes seront présentées : les modèles linéaires, les réseaux de neurones, les réseaux bayésiens dynamiques et les machines à vecteur support (SVM). Enfin, le quatrième chapitre est l'occasion de présenter une méthode de modélisation originale.En effet, après avoir détaillé la mise en oeuvre des méthodes d'identification de représentation d'état, nous verrons comment prendre en compte des a priori théoriques au cours de l'apprentissage de ce type de modèle, à savoir une contrainte de stabilité.
28
Shokri, Razaghi Hooshmand. "Statistical Machine Learning & Deep Neural Networks Applied to Neural Data Analysis." Thesis, 2020. https://doi.org/10.7916/d8-79ec-r948.
Full textAbstract:
Computational neuroscience seeks to discover the underlying mechanisms by which neural activity is generated. With the recent advancement in neural data acquisition methods, the bottleneck of this pursuit is the analysis of ever-growing volume of neural data acquired in numerous labs from various experiments. These analyses can be broadly divided into two categories. First, extraction of high quality neuronal signals from noisy large scale recordings. Second, inference for statistical models aimed at explaining the neuronal signals and underlying processes that give rise to them. Conventionally, majority of the methodologies employed for this effort are based on statistics and signal processing. However, in recent years recruiting Artificial Neural Networks (ANN) for neural data analysis is gaining traction. This is due to their immense success in computer vision and natural language processing, and the stellar track record of ANN architectures generalizing to a wide variety of problems. In this work we investigate and improve upon statistical and ANN machine learning methods applied to multi-electrode array recordings and inference for dynamical systems that play critical roles in computational neuroscience.
In the first and second part of this thesis, we focus on spike sorting problem. The analysis of large-scale multi-neuronal spike train data is crucial for current and future of neuroscience research. However, this type of data is not available directly from recordings and require further processing to be converted into spike trains. Dense multi-electrode arrays (MEA) are standard methods for collecting such recordings. The processing needed to extract spike trains from these raw electrical signals is carried out by ``spike sorting'' algorithms. We introduce a robust and scalable MEA spike sorting pipeline YASS (Yet Another Spike Sorter) to address many challenges that are inherent to this task. We primarily pay attention to MEA data collected from the primate retina for important reasons such as the unique challenges and available side information that ultimately assist us in scoring different spike sorting pipelines. We also introduce a Neural Network architecture and an accompanying training scheme specifically devised to address the challenging task of deconvolution in MEA recordings.
In the last part, we shift our attention to inference for non-linear dynamics. Dynamical systems are the governing force behind many real world phenomena and temporally correlated data. Recently, a number of neural network architectures have been proposed to address inference for nonlinear dynamical systems. We introduce two different methods based on normalizing flows for posterior inference in latent non-linear dynamical systems. We also present gradient-based amortized posterior inference approaches using the auto-encoding variational Bayes framework that can be applied to a wide range of generative models with nonlinear dynamics. We call our method 𝘍𝘪𝘭𝘵𝘦𝘳𝘪𝘯𝘨 𝘕𝘰𝘳𝘮𝘢𝘭𝘪𝘻𝘪𝘯𝘨 𝘍𝘭𝘰𝘸𝘴 (FNF). FNF performs favorably against state-of-the-art inference methods in terms of accuracy of predictions and quality of uncovered codes and dynamics on synthetic data.
29
Fletcher, Lizelle. "Statistical modelling by neural networks." Thesis, 2002. http://hdl.handle.net/10500/600.
Full textAbstract:
In this thesis the two disciplines of Statistics and Artificial Neural Networks
are combined into an integrated study of a data set of a weather modification
Experiment.
An extensive literature study on artificial neural network methodology has
revealed the strongly interdisciplinary nature of the research and the applications
in this field.
An artificial neural networks are becoming increasingly popular with data
analysts, statisticians are becoming more involved in the field. A recursive
algoritlun is developed to optimize the number of hidden nodes in a feedforward
artificial neural network to demonstrate how existing statistical techniques
such as nonlinear regression and the likelihood-ratio test can be applied in
innovative ways to develop and refine neural network methodology.
This pruning algorithm is an original contribution to the field of artificial
neural network methodology that simplifies the process of architecture selection,
thereby reducing the number of training sessions that is needed to find
a model that fits the data adequately.
[n addition, a statistical model to classify weather modification data is developed
using both a feedforward multilayer perceptron artificial neural network
and a discriminant analysis. The two models are compared and the effectiveness
of applying an artificial neural network model to a relatively small
data set assessed.
The formulation of the problem, the approach that has been followed to
solve it and the novel modelling application all combine to make an original
contribution to the interdisciplinary fields of Statistics and Artificial Neural
Networks as well as to the discipline of meteorology.Mathematical Sciences
D. Phil. (Statistics)
30
"Radial basis function of neural network in performance attribution." 2003. http://library.cuhk.edu.hk/record=b5891681.
Full textAbstract:
Wong Hing-Kwok.Thesis (M.Phil.)--Chinese University of Hong Kong, 2003.
Includes bibliographical references (leaves 34-35).
Abstracts in English and Chinese.
Abstract --- p.i
Acknowledgement --- p.iii
Chapter 1 --- Introduction --- p.1
Chapter 2 --- Radial Basis Function (RBF) of Neural Network --- p.5
Chapter 2.1 --- Neural Network --- p.6
Chapter 2.2 --- Radial Basis Function (RBF) Network --- p.8
Chapter 2.3 --- Model Specification --- p.10
Chapter 2.4 --- Estimation --- p.12
Chapter 3 --- RBF in Performance Attribution --- p.17
Chapter 3.1 --- Background of Data Set --- p.18
Chapter 3.2 --- Portfolio Construction --- p.20
Chapter 3.3 --- Portfolio Rebalance --- p.22
Chapter 3.4 --- Result --- p.23
Chapter 4 --- Comparison --- p.26
Chapter 4.1 --- Standard Linear Model --- p.27
Chapter 4.2 --- Fixed Additive Model --- p.28
Chapter 4.3 --- Refined Additive Model --- p.29
Chapter 4.4 --- Result --- p.30
Chapter 5 --- Conclusion --- p.32
Bibliography --- p.34
32
Herman, Hilde. "Benchmarking a neural network forecaster against statistical measures." Thesis, 2014. http://hdl.handle.net/10210/12098.
Full textAbstract:
M.Ing. (Mechanical Engineering)The combination of non-linear signal processing and financial market forecasting is a relatively new field of research. This dissertation concerns the forecasting of shares quoted on the Johannesburg Stock Exchange by using Artificial Neural Networks, and does so by comparing neural network results with established statistical results. The share price rise or fall are predicted as well as buy, sell and hold signals and compared to Time Series model and Moving Average Convergence Divergence results. The dissertation will show that artificial neural networks predict the share price rise or fall with less error than statistical models and yielded the highest profit when forecasting buy, sell and hold signals for a particular share.
33
Wang, Haiyan. "Statistical pattern recognition based on LVQ artificial neural networks : application to TATA box motif." Thesis, 2000. http://hdl.handle.net/10321/1861.
Full textAbstract:
Dissertation submitted in compliance with the requirements for Masters Degree in Technology in the Department of Electrical Engineering (Light Current, Technikon Natal, 2000.The computational analysis of eukaryotic promoters are among the most important and complex research domains that may contribute to complete gene identification. The current methods for promoter recognition are not sufficiently developed. Eukaryotic promoters contain a number of short motifs that may be used in promoter recognition. Having good computational models for these motifs can be crucial for increased efficiency of promoter recognition programs. This study proposes a combined statistical and LVQ neural network system as a computational model of the TAT A box motif of eukaryotic promoters. The methodology used is universal and applicable to any short functional motif in DNA. The statistical analysis of the core TAT A motif hexamer and its neighboring haxamers show strong regularities that can be used in motif recognition. Moreover, the positional distribution of the TAT A motif in terms of its distance from the transcription start site is very regular and is used in the statistical modeling. Furthermore, the matching score of the position weight matrix for the motif was used as a part of the model. Based on these statistical properties. a novel LV Q classifier for TAT A motif recognition is developed. The characteristics of the method are that the genetic algorithm was used for finding good initial weights of the LV Q system, while fine tuning of two LVQ networks was done by the lvq? algorithm. The final computational model is developed for a recognition level of 67.8o/c correct recognition on the test set with less than 1% false recognition. This model is evaluated in the task of promoter recognition on an independent test set. The results in promoter recognition outperform three other promoter recognition programs. It is shown that the recognition of promoters based on the recognition of the TAT A motifs using this new model is superior to the recognition based on the currently used position weight matrix description of this motif.
M
34
Takikawa, Masami. "Representations and algorithms for efficient inference in Bayesian networks." Thesis, 1998. http://hdl.handle.net/1957/33530.
Full textAbstract:
Bayesian networks are used for building intelligent agents that act under uncertainty. They are a compact representation of agents' probabilistic knowledge. A Bayesian network can be viewed as representing a factorization of a full joint probability distribution into the multiplication of a set of conditional probability distributions. Independence of causal influence enables one to further factorize the conditional probability distributions into a combination of even smaller factors. The efficiency of inference in Bayesian networks depends on how these factors are combined. Finding an optimal combination is NP-hard.
We propose a new method for efficient inference in large Bayesian networks, which is a combination of new representations and new combination algorithms. We present new, purely multiplicative representations of independence of causal influence models. They are easy to use because any standard inference algorithm can work with them. Also, they allow for exploiting independence of causal influence fully because they do not impose any constraints on combination ordering. We develop combination algorithms that work with heuristics. Heuristics are generated automatically by using machine learning techniques. Empirical studies, based on the CPCS network for medical diagnosis, show that this method is more efficient and allows for inference in larger networks than existing methods.Graduation date: 1999
35
Janakiraman, V. "Statistical Leakage Analysis Framework Using Artificial Neural Networks Considering Process And Environmental Variations." Thesis, 2011. http://etd.iisc.ernet.in/handle/2005/2098.
Full textAbstract:
Leakage current and process variations are two primary hurdles in modern VLSI design. It depends exponentially on process and environmental parameters and hence small variations in these result in a large spread in leakage current of manufactured dies. Traditionally, Exponential Quadratic(EQ) models have been used to model leakage current as a function of process parameters which can model limited non-linearity and hence become inaccurate for large process variations. Artificial Neural Networks (ANN) have shown great promise in modeling circuit parameters for CAD applications. We model leakage with ANN models which perform better than the EQ models for increased process variations. However, the complex nature of the ANN model, with the standard sigmoidal activation functions, does not allow analytical expressions for its mean and variance for the case of Gaussian process variations. We propose the use of a new activation function that allows us to derive an analytical expression for the mean and a semi-analytical expression for the variance of the ANN based leakage model. To the best of our knowledge this is the first result in this direction. All existing SLA frameworks are closely tied to the EQ leakage model and hence fail to work with sophisticated ANN models. We therefore set up an SLA framework that can efficiently work with these ANN models. Results show that the CDF of leakage current of ISCAS'85 circuits can be predicted accurately with the error in mean and standard deviation, compared to Monte Carlo based simulations, being less than 1\% and 2\% respectively across a range of voltage and temperature values. The complexity of our framework is similar to existing SLA frameworks yet more accurate over a larger range of variations. Ignoring the thermal profile of the chip leads to a gross error of nearly 50\% in the prediction of leakage yield. Our neural network model also includes the voltage and temperature as input parameters, thereby enabling voltage and temperature aware statistical leakage analysis (SLA). Similarly leakage CDF can be predicted across a range of supply and body voltages since they are both part of the model. Our framework used analytical techniques to account for local variations and Monte Carlo techniques for global variations and hence it can also be used for Non-Gaussian global variations.
36
"Learning Bayesian networks using evolutionary computation and its application in classification." 2001. http://library.cuhk.edu.hk/record=b5890754.
Full textAbstract:
by Lee Shing-yan.Thesis (M.Phil.)--Chinese University of Hong Kong, 2001.
Includes bibliographical references (leaves 126-133).
Abstracts in English and Chinese.
Chapter 1 --- Introduction --- p.1
Chapter 1.1 --- Problem Statement --- p.4
Chapter 1.2 --- Contributions --- p.4
Chapter 1.3 --- Thesis Organization --- p.5
Chapter 2 --- Background --- p.7
Chapter 2.1 --- Bayesian Networks --- p.7
Chapter 2.1.1 --- A Simple Example [42] --- p.8
Chapter 2.1.2 --- Formal Description and Notations --- p.9
Chapter 2.1.3 --- Learning Bayesian Network from Data --- p.14
Chapter 2.1.4 --- Inference on Bayesian Networks --- p.18
Chapter 2.1.5 --- Applications of Bayesian Networks --- p.19
Chapter 2.2 --- Bayesian Network Classifiers --- p.20
Chapter 2.2.1 --- The Classification Problem in General --- p.20
Chapter 2.2.2 --- Bayesian Classifiers --- p.21
Chapter 2.2.3 --- Bayesian Network Classifiers --- p.22
Chapter 2.3 --- Evolutionary Computation --- p.28
Chapter 2.3.1 --- Four Kinds of Evolutionary Computation --- p.29
Chapter 2.3.2 --- Cooperative Coevolution --- p.31
Chapter 3 --- Bayesian Network Learning Algorithms --- p.33
Chapter 3.1 --- Related Work --- p.34
Chapter 3.1.1 --- Using GA --- p.34
Chapter 3.1.2 --- Using EP --- p.36
Chapter 3.1.3 --- Criticism of the Previous Approaches --- p.37
Chapter 3.2 --- Two New Strategies --- p.38
Chapter 3.2.1 --- A Hybrid Framework --- p.38
Chapter 3.2.2 --- A New Operator --- p.39
Chapter 3.3 --- CCGA --- p.44
Chapter 3.3.1 --- The Algorithm --- p.45
Chapter 3.3.2 --- CI Test Phase --- p.46
Chapter 3.3.3 --- Cooperative Coevolution Search Phase --- p.47
Chapter 3.4 --- HEP --- p.52
Chapter 3.4.1 --- A Novel Realization of the Hybrid Framework --- p.54
Chapter 3.4.2 --- Merging in HEP --- p.55
Chapter 3.4.3 --- Prevention of Cycle Formation --- p.55
Chapter 3.5 --- Summary --- p.56
Chapter 4 --- Evaluation of Proposed Learning Algorithms --- p.57
Chapter 4.1 --- Experimental Methodology --- p.57
Chapter 4.2 --- Comparing the Learning Algorithms --- p.61
Chapter 4.2.1 --- Comparing CCGA with MDLEP --- p.63
Chapter 4.2.2 --- Comparing HEP with MDLEP --- p.65
Chapter 4.2.3 --- Comparing CCGA with HEP --- p.68
Chapter 4.3 --- Performance Analysis of CCGA --- p.70
Chapter 4.3.1 --- Effect of Different α --- p.70
Chapter 4.3.2 --- Effect of Different Population Sizes --- p.72
Chapter 4.3.3 --- Effect of Varying Crossover and Mutation Probabilities --- p.73
Chapter 4.3.4 --- Effect of Varying Belief Factor --- p.76
Chapter 4.4 --- Performance Analysis of HEP --- p.77
Chapter 4.4.1 --- The Hybrid Framework and the Merge Operator --- p.77
Chapter 4.4.2 --- Effect of Different Population Sizes --- p.80
Chapter 4.4.3 --- Effect of Different --- p.81
Chapter 4.4.4 --- Efficiency of the Merge Operator --- p.84
Chapter 4.5 --- Summary --- p.85
Chapter 5 --- Learning Bayesian Network Classifiers --- p.87
Chapter 5.1 --- Issues in Learning Bayesian Network Classifiers --- p.88
Chapter 5.2 --- The Multinet Classifier --- p.89
Chapter 5.3 --- The Augmented Bayesian Network Classifier --- p.91
Chapter 5.4 --- Experimental Methodology --- p.94
Chapter 5.5 --- Experimental Results --- p.97
Chapter 5.6 --- Discussion --- p.103
Chapter 5.7 --- Application in Direct Marketing --- p.106
Chapter 5.7.1 --- The Direct Marketing Problem --- p.106
Chapter 5.7.2 --- Response Models --- p.108
Chapter 5.7.3 --- Experiment --- p.109
Chapter 5.8 --- Summary --- p.115
Chapter 6 --- Conclusion --- p.116
Chapter 6.1 --- Summary --- p.116
Chapter 6.2 --- Future Work --- p.118
Chapter A --- A Supplementary Parameter Study --- p.120
Chapter A.1 --- Study on CCGA --- p.120
Chapter A.1.1 --- Effect of Different α --- p.120
Chapter A.1.2 --- Effect of Different Population Sizes --- p.121
Chapter A.1.3 --- Effect of Varying Crossover and Mutation Probabilities --- p.121
Chapter A.1.4 --- Effect of Varying Belief Factor --- p.122
Chapter A.2 --- Study on HEP --- p.123
Chapter A.2.1 --- The Hybrid Framework and the Merge Operator --- p.123
Chapter A.2.2 --- Effect of Different Population Sizes --- p.124
Chapter A.2.3 --- Effect of Different Δα --- p.124
Chapter A.2.4 --- Efficiency of the Merge Operator --- p.125
37
Gutterman, Craig. "Learning for Network Applications and Control." Thesis, 2021. https://doi.org/10.7916/d8-3bhx-p234.
Full textAbstract:
The emergence of new Internet applications and technologies have resulted in an increased complexity as well as a need for lower latency, higher bandwidth, and increased reliability. This ultimately results in an increased complexity of network operation and management. Manual management is not sufficient to meet these new requirements.
There is a need for data driven techniques to advance from manual management to autonomous management of network systems. One such technique, Machine Learning (ML), can use data to create models from hidden patterns in the data and make autonomous modifications. This approach has shown significant improvements in other domains (e.g., image recognition and natural language processing). The use of ML, along with advances in programmable control of Software- Defined Networks (SDNs), will alleviate manual network intervention and ultimately aid in autonomous network operations. However, realizing a data driven system that can not only understand what is happening in the network but also operate autonomously requires advances in the networking domain, as well as in ML algorithms.
In this thesis, we focus on developing ML-based network architectures and data driven net- working algorithms whose objective is to improve the performance and management of future networks and network applications. We focus on problems spanning across the network protocol stack from the application layer to the physical layer. We design algorithms and architectures that are motivated by measurements and observations in real world or experimental testbeds.
In Part I we focus on the challenge of monitoring and estimating user video quality of experience (QoE) of encrypted video traffic for network operators. We develop a system for REal-time QUality of experience metric detection for Encrypted Traffic, Requet. Requet uses a detection algorithm to identify video and audio chunks from the IP headers of encrypted traffic. Features extracted from the chunk statistics are used as input to a random forest ML model to predict QoE metrics. We evaluate Requet on a YouTube dataset we collected, consisting of diverse video assets delivered over various WiFi and LTE network conditions. We then extend Requet, and present a study on YouTube TV live streaming traffic behavior over WiFi and cellular networks covering a 9-month period. We observed pipelined chunk requests, a reduced buffer capacity, and a more stable chunk duration across various video resolutions compared to prior studies of on-demand streaming services. We develop a YouTube TV analysis tool using chunks statistics detected from the extracted data as input to a ML model to infer user QoE metrics.
In Part II we consider allocating end-to-end resources in cellular networks. Future cellular networks will utilize SDN and Network Function Virtualization (NFV) to offer increased flexibility for network infrastructure operators to utilize network resources. Combining these technologies with real-time network load prediction will enable efficient use of network resources. Specifically, we leverage a type of recurrent neural network, Long Short-Term Memory (LSTM) neural networks, for (i) service specific traffic load prediction for network slicing, and (ii) Baseband Unit (BBU) pool traffic load prediction in a 5G cloud Radio Access Network (RAN). We show that leveraging a system with better accuracy to predict service requirements results in a reduction of operation costs.
We focus on addressing the optical physical layer in Part III. Greater network flexibility through SDN and the growth of high bandwidth services are motivating faster service provisioning and capacity management in the optical layer. These functionalities require increased capacity along with rapid reconfiguration of network resources. Recent advances in optical hardware can enable a dramatic reduction in wavelength provisioning times in optical circuit switched networks. To support such operations, it is imperative to reconfigure the network without causing a drop in service quality to existing users. Therefore, we present a ML system that uses feedforward neural networks to predict the dynamic response of an optically circuit-switched 90-channel multi-hop Reconfigurable Optical Add-Drop Multiplexer (ROADM) network. We show that the trained deep neural network can recommend wavelength assignments for wavelength switching with minimal power excursions. We extend the performance of the ML system by implementing and testing a Hybrid Machine Learning (HML) model, which combines an analytical model with a neural network machine learning model to achieve higher prediction accuracy.
In Part IV, we use a data-driven approach to address the challenge of wireless content delivery in crowded areas. We present the Adaptive Multicast Services (AMuSe) system, whose objective is to enable scalable and adaptive WiFi multicast. Specifically, we develop an algorithm for dynamic selection of a subset of the multicast receivers as feedback nodes. Further, we describe the Multicast Dynamic Rate Adaptation (MuDRA) algorithm that utilizes AMuSe’s feedback to optimally tune the physical layer multicast rate. Our experimental evaluation of MuDRA on the ORBIT testbed shows that MuDRA outperforms other schemes and supports high throughput multicast flows to hundreds of nodes while meeting quality requirements. We leverage the lessons learned from AMuSe for WiFi and use order statistics to address the performance issues with LTE evolved Multimedia Broadcast/Multicast Service (eMBMS). We present the Dynamic Monitoring (DyMo) system which provides low-overhead and real-time feedback about eMBMS performance to be used for network optimization. We focus on the Quality of Service (QoS) Evaluation module and develop a Two-step estimation algorithm which can efficiently identify the SNR Threshold as a one time estimation. DyMo significantly outperforms alternative schemes based on the Order-Statistics estimation method which relies on random or periodic sampling.
38
Merel, Joshua Scott. "New perspectives on learning, inference, and control in brains and machines." Thesis, 2016. https://doi.org/10.7916/D8C8296C.
Full textAbstract:
The work presented in this thesis provides new perspectives and approaches for problems that arise in the analysis of neural data. Particular emphasis is placed on parameter fitting and automated analysis problems that would arise naturally in closed-loop experiments. Part one focuses on two brain-computer interface problems. First, we provide a framework for understanding co-adaptation, the setting in which decoder updating and user learning occur simultaneously. We also provide a new perspective on intention-based parameter fitting and tools to extend this approach to higher dimensional decoders. Part two focuses on event inference, which refers to the decomposition of observed timeseries data into interpretable events. We present application of event inference methods on voltage-clamp recordings as well as calcium imaging, and describe extensions to allow for combining data across modalities or trials.
39
Ghane, Parisa. "Silent speech recognition in EEG-based brain computer interface." Thesis, 2015. http://hdl.handle.net/1805/9886.
Full textAbstract:
Indiana University-Purdue University Indianapolis (IUPUI)A Brain Computer Interface (BCI) is a hardware and software system that establishes direct communication between human brain and the environment. In a BCI system, brain messages pass through wires and external computers instead of the normal pathway of nerves and muscles. General work ow in all BCIs is to measure brain activities, process and then convert them into an output readable for a computer. The measurement of electrical activities in different parts of the brain is called electroencephalography (EEG). There are lots of sensor technologies with different number of electrodes to record brain activities along the scalp. Each of these electrodes captures a weighted sum of activities of all neurons in the area around that electrode. In order to establish a BCI system, it is needed to set a bunch of electrodes on scalp, and a tool to send the signals to a computer for training a system that can find the important information, extract them from the raw signal, and use them to recognize the user's intention. After all, a control signal should be generated based on the application. This thesis describes the step by step training and testing a BCI system that can be used for a person who has lost speaking skills through an accident or surgery, but still has healthy brain tissues. The goal is to establish an algorithm, which recognizes different vowels from EEG signals. It considers a bandpass filter to remove signals' noise and artifacts, periodogram for feature extraction, and Support Vector Machine (SVM) for classification.
40
Rebout, Lise. "L’extraction de phrases en relation de traduction dans Wikipédia." Thèse, 2012. http://hdl.handle.net/1866/8614.
Full textAbstract:
Afin d'enrichir les données de corpus bilingues parallèles, il peut être judicieux de travailler avec des corpus dits comparables. En effet dans ce type de corpus, même si les documents dans la langue cible ne sont pas l'exacte traduction de ceux dans la langue source, on peut y retrouver des mots ou des phrases en relation de traduction.
L'encyclopédie libre Wikipédia constitue un corpus comparable multilingue de plusieurs millions de documents. Notre travail consiste à trouver une méthode générale et endogène permettant d'extraire un maximum de phrases parallèles. Nous travaillons avec le couple de langues français-anglais mais notre méthode, qui n'utilise aucune ressource bilingue extérieure, peut s'appliquer à tout autre couple de langues.
Elle se décompose en deux étapes. La première consiste à détecter les paires d’articles qui ont le plus de chance de contenir des traductions. Nous utilisons pour cela un réseau de neurones entraîné sur un petit ensemble de données constitué d'articles alignés au niveau des phrases. La deuxième étape effectue la sélection des paires de phrases grâce à un autre réseau de neurones dont les sorties sont alors réinterprétées par un algorithme d'optimisation combinatoire et une heuristique d'extension.
L'ajout des quelques 560~000 paires de phrases extraites de Wikipédia au corpus d'entraînement d'un système de traduction automatique statistique de référence permet d'améliorer la qualité des traductions produites.
Nous mettons les données alignées et le corpus extrait à la disposition de la communauté scientifique.Working with comparable corpora can be useful to enhance bilingual parallel corpora. In fact, in such corpora, even if the documents in the target language are not the exact translation of those in the source language, one can still find translated words or sentences. The free encyclopedia Wikipedia is a multilingual comparable corpus of several millions of documents. Our task is to find a general endogenous method for extracting a maximum of parallel sentences from this source. We are working with the English-French language pair but our method -- which uses no external bilingual resources -- can be applied to any other language pair. It can best be described in two steps. The first one consists of detecting article pairs that are most likely to contain translations. This is achieved through a neural network trained on a small data set composed of sentence aligned articles. The second step is to perform the selection of sentence pairs through another neural network whose outputs are then re-interpreted by a combinatorial optimization algorithm and an extension heuristic. The addition of the 560~000 pairs of sentences extracted from Wikipedia to the training set of a baseline statistical machine translation system improves the quality of the resulting translations. We make both the aligned data and the extracted corpus available to the scientific community.