Extreme learning machine for a new hybrid morphological/linear perceptron

Autor(es)

Sussner, Peter ^[1] ; Campiotti, Israel ^[2]

Afiliação do(s) autor(es)

^[1] Univ Estadual Campinas, Dept Appl Math, BR-13083859 Campinas, SP - Brazil

^[2] Parque Tecnol Unicamp, NeuralMind, Av Alan Turing 345, Sala 5, BR-13083898 Campinas, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: NEURAL NETWORKS; v. 123, p. 288-298, MAR 2020.
• Citações Web of Science: 1

Resumo

Morphological neural networks (MNNs) can be characterized as a class of artificial neural networks that perform an operation of mathematical morphology at every node, possibly followed by the application of an activation function. Morphological perceptrons (MPs) and (gray-scale) morphological associative memories are among the most widely known MNN models. Since their neuronal aggregation functions are not differentiable, classical methods of non-linear optimization can in principle not be directly applied in order to train these networks. The same observation holds true for hybrid morphological/linear perceptrons and other related models. Circumventing these problems of non-differentiability, this paper introduces an extreme learning machine approach for training a hybrid morphological/linear perceptron, whose morphological components were drawn from previous MP models. We apply the resulting model to a number of well-known classification problems from the literature and compare the performance of our model with the ones of several related models, including some recent MNNs and hybrid morphological/linear neural networks. (C) 2019 Elsevier Ltd. All rights reserved. (AU)

• Processo FAPESP: 17/10224-4 - Perceptrons híbridos fuzzy morfológicos/lineares baseados em extreme learning com aplicações em classificação
• Beneficiário: Israel Campiotti
• Linha de fomento: Bolsas no Brasil - Iniciação Científica
• Processo FAPESP: 18/13657-1 - Algumas abordagens de computação em reticulados a inteligência computacional, processamento e análise de imagens
• Beneficiário: Peter Sussner
• Linha de fomento: Auxílio à Pesquisa - Regular