Presentation | 2002/6/18 A Neural Network Model with a Chaotic Neuron for Discrete Data Processing Hiroshi SUGIMOTO, Masaharu ADACHI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this article, an artificial neural network model whose hidden and context layers are replaced by a chaotic neuron model is proposed. The network is initially trained as Elman type network with a symbol sequence. Then, the hidden and context layers are replaced by a chaotic neuron model but the synaptic weights and biases in the hidden layer are kept as the result of the training. The network with the chaotic neuron shows chaotic response that suggesting the possibility the symbol processing with chaotic dynamics. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Chaotic neuron model / Elman network / Symbol processing |
Paper # | NLP2002-24 |
Date of Issue |
Conference Information | |
Committee | NLP |
---|---|
Conference Date | 2002/6/18(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Nonlinear Problems (NLP) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Neural Network Model with a Chaotic Neuron for Discrete Data Processing |
Sub Title (in English) | |
Keyword(1) | Chaotic neuron model |
Keyword(2) | Elman network |
Keyword(3) | Symbol processing |
1st Author's Name | Hiroshi SUGIMOTO |
1st Author's Affiliation | Department of Electronic Engineering, Graduate School of Engineering, Tokyo Denki University() |
2nd Author's Name | Masaharu ADACHI |
2nd Author's Affiliation | Department of Electronic Engineering, Graduate School of Engineering, Tokyo Denki University |
Date | 2002/6/18 |
Paper # | NLP2002-24 |
Volume (vol) | vol.102 |
Number (no) | 142 |
Page | pp.pp.- |
#Pages | 4 |
Date of Issue |