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).

Thesis (M. A.)--University of North Texas, May, 2007. / Title from title page display. Includes bibliographical references.

Thesis (M.S.)--Virginia Polytechnic Institute and State University, 1994. / Vita. Abstract. Includes bibliographical references (leaves 155-159). Also available via the Internet.

Η παρούσα διπλωματική εργασία αποσκοπεί στη μελέτη και την εκπαίδευση των Τεχνητών Νευρωνικών Δικτύων με τη βοήθεια γνωστών μεθόδων, όπως τη μέθοδο όπισθεν διάδοσης σφάλματος (back-propagation), τη μέθοδο adaptive back-propagation, τη momentum back-propagtion και την resilient propagation (RPROP) και τη σύγκριση αυτών. Κατά τη διάρκεια αυτή της εργασίας παρουσιάσαμε τις βασικές αρχιτεκτονικές των Τεχνητών Νευρωνικών Δικτύων και τις διάφορες μεθόδους εκπαίδευσης τους. Μελετήσαμε τις τεχνικές βελτιστοποίησης απόδοσης ενός δικτύου με τη χρήση αλγορίθμων και περιγράψαμε τη γνωστή μέθοδο όπισθεν διάδοσης σφάλματος (back-propagation) αλλά και παραλλαγές αυτής. Τέλος, δώσαμε τα πειραματικά αποτελέσματα από την εκπαίδευση των Τεχνητών Νευρωνικών Δικτύων, με τη βοήθεια των παραπάνω αλγορίθμων, σε πολύ γνωστά και ευρέως χρησιμοποιημένα χαρακτηριστικά προβλήματα πραγματικού κόσμου. / The purpose of this thesis is to study and train Artificial Neural Networks with the help of well-known methods, such as the back-propagation method, the adaptive back-propagation method, the momentum back-propagation method and the resilient propagation (RPROP) method, and also to implement a comparison between them. During this project we introduced the basic architectures of Artificial Neural Networks and the various methods for their training. We studied the techniques for optimizing the performance of a network with the use of algorithms and described the well-known back-propagation method but also her variations. Finally, we gave the experimental results from the training of the Neural Networks, with the help of the previous mentioned algorithms, in widely known and commonly used characteristical problems of the real world.

The issue of robust training is tackled for fixed multilayer feedforward architectures. Several researchers have proved the theoretical capabilities of Multilayer Feedforward networks but in practice the robust convergence of standard methods like standard backpropagation, conjugate gradient descent and Quasi-Newton methods may be poor for various problems. It is suggested that the common assumptions about the overall surface shape break down when many individual component surfaces are combined and robustness suffers accordingly. A new method to train Multilayer Feedforward networks is presented in which no particular shape is assumed for the surface and where an attempt is made to optimally combine the individual components of a solution for the overall solution. The method is based on computing Tangent Hyperplanes to the non-linear solution manifolds. At the core of the method is a mechanism to minimise the sum of squared errors and as such its use is not limited to Neural Networks. The set of tests performed for Neural Networks show that the method is very robust regarding convergence of training and has a powerful ability to find good directions in weight space. Generalisation is also a very important issue in Neural Networks and elsewhere. Neural Networks are expected to provide sensible outputs for unseen inputs. A framework for hyperplane based classifiers is presented for improving average generalisation. The framework attempts to establish a trained boundary so that there is an optimal overall spacing from the boundary to training points closest to this boundary. The framework is shown to provide results consistent with the theoretical expectations.

Neural networks can be analysed from two points of view: training and generalisation. The training is characterised by a trade-off between the 'goodness' of the training algorithm itself (speed, reliability, guaranteed convergence) and the 'goodness' of the architecture (the difficulty of the problems the network can potentially solve). Good training algorithms are available for simple architectures which cannot solve complicated problems. More complex architectures, which have been shown to be able to solve potentially any problem do not have in general simple and fast algorithms with guaranteed convergence and high reliability. A good training technique should be simple, fast and reliable, and yet also be applicable to produce a network able to solve complicated problems. The thesis presents Constraint Based Decomposition (CBD) as a technique which satisfies the above requirements well. CBD is shown to build a network able to solve complicated problems in a simple, fast and reliable manner. Furthermore, the user is given a better control over the generalisation properties of the trained network with respect to the control offered by other techniques. The generalisation issue is addressed, as well. An analysis of the meaning of the term "good generalisation" is presented and a framework for assessing generalisation is given: the generalisation can be assessed only with respect to a known or desired underlying function. The known properties of the underlying function can be embedded into the network thus ensuring a better generalisation for the given problem. This is the fundamental idea of the complex backpropagation network. This network can associate signals through associating some of their parameters using complex weights. It is shown that such a network can yield better generalisation results than a standard backpropagation network associating instantaneous values.

The interatomic potential is a mathematical model that describes the chemistry occurring at the atomic level. It provides a functional mapping between the atomic nuclei coordinates and the total potential energy of a system. This thesis investigates three aspects of interatomic potentials, the first of which is the simulation of materials at the atomic scale using classical molecular dynamics (MD). Molecular dynamics code is used to follow the evolution of a system of discrete particles through time and is employed here to model the bombardment of fullerite films modified with low dose Argon ion impacts.

System identification is the task of constructing representative models of processes and has become an invaluable tool in many different areas of science and engineering. Due to the inherent complexity of many real world systems the application of traditional techniques is limited. In such instances more sophisticated (so called intelligent) modelling approaches are required. Neurofuzzy modelling is one such technique, which by integrating the attributes of fuzzy systems and neural networks is ideally suited to system identification. This attractive paradigm combines the well established learning techniques of a particular form of neural network i.e. generalised linear models with the transparent knowledge representation of fuzzy systems, thus producing models which possess the ability to learn from real world observations and whose behaviour can be described naturally as a series of linguistic humanly understandable rules. Unfortunately, the application of these systems is limited to low dimensional problems for which good quality expert knowledge and data are available. The work described in this thesis addresses this fundamental problem with neurofuzzy modelling, as a result algorithms which are less sensitive to the quality of the a priori knowledge and empirical data are developed. The true modelling capabilities of any strategy is heavily reliant on the model's structure, and hence an important (arguably the most important) task is structure identification. Also, due to the curse of dimensionality, in high dimensional problems the size of conventional neurofuzzy models gets prohibitively large. These issues are tackled by the development of automatic neurofuzzy model identification algorithms, which exploit the available expert knowledge and empirical data. To alleviate problems associated with the curse of dimensionality, aid model generalisation and enhance model transparency, parsimonious models are identified. This is achieved by the application of additive and multiplicative neurofuzzy models which exploit structural redundancies found in conventional systems. The developed construction algorithms successfully identify parsimonious models, but as a result of noisy and poorly distributed empirical data, these models can still generalise inadequately. This problem is addressed by the application of Bayesian inferencing techniques; a form of regularisation. Smooth model outputs are assumed and superfluous model parameters are controlled, sufficiently aiding model generalisation and transparency, and data interpolation and extrapolation. By exploiting the structural decomposition of the identified neurofuzzy models, an efficient local method of regularisation is developed. All the methods introduced in this thesis are illustrated on many different examples, including simulated time series, complex functional equations, and multi-dimensional dynamical systems. For many of these problems conventional neurofuzzy modelling is unsuitable, and the developed techniques have extended the range of problems to which neurofuzzy modelling can successfully be applied.

Made available in DSpace on 2014-06-11T19:32:22Z (GMT). No. of bitstreams: 0 Previous issue date: 2011-08-09Bitstream added on 2014-06-13T21:04:12Z : No. of bitstreams: 1 pontes_fj_dr_guara.pdf: 2076253 bytes, checksum: e0151bbfd7f5dd6f59a5364cd9097f4d (MD5) / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / O presente trabalho oferece contribuições à modelagem da rugosidade da peça em processos de usinagem por meio de redes neurais artificiais. Propõe-se um método para o projeto de redes. Perceptron Multi-Camada (Multi-Layer Percepton, ou MLO) e Função de Base radial Radial Basis Function, ou RBF) otimizadas para a predição da rugosidade da pela (Ra). Desenvolve-se um algoritmo que utiliza de forma hibrida a metodologia do projeto de experimentos por meio das técnicas dos fatoriais completose de Variações Evolucionária em Operações (EVOP). A estratégia adotada é a de utilizar o projeto de experimentos na busca de configurações de rede que favoreçam estatisticamente o desempenho na tarefa de predição. Parâmetro de corte dos processos de usinagem são utilizados como entradas das redes. O erro médio absoluto em porcentagem (MAE %) do decil inferioir das observações de predição para o conjunto de testes é utilizado como medida de desempnho dos modelos. Com o objetivo de validar o métido proposto são empregados casos de treinamento gerados a partir de daods obtidos de trabalhos de literatura e de experimentos de torneamento do aço ABNT 121.13. O método proposto leva á redução significativa do erro de predição da rugosidade nas operações de usinagem estudadas, quando se compara seu desempenho ao apresentado por modelos de regressão, aos resultados relatados pela literatura e ao desempenho de modelos neurais propostos por um pacotecomputacional comercial para otimização de configurações de rede. As redes projetadas segundo o método proposto possuem dispersão dos erros de predição significativamente reduzidos na comparação. Observa-se ainda que rede MLP atingem resultados estatisticamente superior aos obtidos pelas melhores redes RBF / The present work offers some contributions to the area of surface roughness modeling by Artificial Neural Network in machining processes. Ir proposes a method for the project networks of MLP (Multi-Layer Perceptron) and RBF (Radial Basis Function) architectures optimized for prediction of Average Surface Roughness (Ru). The methid is expressed in the format of an algorithm employing two techniques from the DOE (Design of Experiments) methodology: Full factorials and Evolutionary Operations(EVOP). The strategy adopted consists in the sistematic use of DOE in a search for network configurations that benefits performance in roughess prediction. Cutting para meters from machining operations are employed as network inputs. Themean absolute error in percentage (MAE%) of the lower decile of the predictions for the test set is used as a figure of merit for network performance. In order to validate the method, data sets retrieved from literature, as well as results of experiments with AISI/SAE free-machining steel, are employed to form training and test data sets for the networks. The proposed algorithm leads to significant reduction in prediction error for surface roughness when compared to the performance delivred by a regression model, by the networks proposed by the original studies data was borrowed from and when compared models proposed by a software package intend to search automatically for optimal network configurations. In addition, networks designed acording to the proposed algorithm displayed reduced dispersion of prediction error for surface roughness when compared to the performance delivered by a regression model, by the networks proposed by the original studies data was borrowed from and when compared to neural models proposed by a software package intended to searchautomatically for optimal network configurations. In addition, networks designed according to the proposed algorith ... (Complete abstract click electronic access below)

Dentre as inúmeras técnicas de conversão de voz utilizadas atualmente, aquelas baseadas em bancos de filtros wavelet, associadas com redes neurais artificiais,têm se destacado. Este trabalho se concentra em tais técnicas, realizando um estudo que relaciona qual a melhor wavelet para conversão de determinados padrões de voz, apresentando uma análise detalhada de quais são as características que levam a estes resultados. Os testes são realizados com vozes da base de dados TIMIT do Linguistic Data Consortium (LDC). / Dentre as inúmeras técnicas de conversão de voz utilizadas atualmente, aquelas baseadas em bancos de filtros wavelet, associadas com redes neurais artificiais, têm se destacado. Este trabalho se concentra em tais técnicas, realizando um estudo que relaciona qual a melhor wavelet para conversão de determinados padrões de voz, apresentando uma análise detalhada de quais são as características que levam a estes resultados. Os testes são realizados com vozes da base de dados TIMIT do Linguistic Data Consortium (LDC).