Modelos modificados de redes neurais morfológicas / Modified models of morphological neural networks
AUTOR(ES)
Estevão Esmi Laureano
FONTE
IBICT - Instituto Brasileiro de Informação em Ciência e Tecnologia
DATA DE PUBLICAÇÃO
26/04/2010
RESUMO
Morphological neural networks (MNN) are artificial neural networks whose hidden neurons perform elementary operations of mathematical morphology (MM). Several particular models of MNNs have been proposed in recent years, including morphological perceptrons (MPs), morphological perceptrons with dendrites, (fuzzy) morphological associative memories, modular morphological neural networks as well as morphological shared-weight and regularization neural networks. Applications of MNNs include pattern recognition, time series prediction, target detection, self-location, and hyper-spectral image processing. In this thesis, we present two new models of morphological neural networks. The first one consists of a fuzzy associative memory called KS-FAM. The second one represents a novel version of the morphological perceptron for classification problems with multiple classes called morphological perceptron with competitive learning(MP/CL). For both KS-FAM and MP/CL models, we investigated and showed several properties. In particular, we characterized the conditions for perfect recall using the KS-FAM as well as the outputs produced upon presentation of an arbitrary input patern. In addition, we proved that the learning algorithm of the MP/CL converges in a finite number of steps and that the results produced after the conclusion of the training phase do not depend on the order in which the training patterns are presented to the network. Moreover, the MP/CL is guaranteed to perfectly classify all training data without generating any regions of indecision. Finaly, we compared the performances of our new models and a range of competing models in terms of a series of experiments in gray-scale image recognition (in case of the KS-FAM) and classification using several well-known datasets that are available on the internet (in case of the MP/CL)
ASSUNTO(S)
teoria dos reticulados morfologia matemática conjuntos difusos redes neurais (computação) memória associativa reconhecimento de padrões lattice theory mathematical morphology fuzzy sets neural networks (computer science) associative memory pettern
ACESSO AO ARTIGO
http://libdigi.unicamp.br/document/?code=000771252Documentos Relacionados
- Metodologia para elaboração de modelos de fragilidade ambiental utilizando redes neurais
- REGIME-SWITCHING MODELS: THRESHOLDS, SMOOTH TRANSITIONS, AND NEURAL NETWORKS
- Redes neurais morfologicas : alguns aspectos teoricos e resultados experimentais em problemas de classificação
- Utilização de redes neurais na determinação de modelos geoidais
- Modelos lineares locais para identificaÃÃo de sistemas dinÃmicos usando redes neurais competitivas