Presentation | 2007-03-16 Learning of CA rules by Digital Multi-Layer-Perceptrons Toru ABE, Toshimichi SAITO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | This paper studies learning of Binary Neural Networks (BNNs) that is a simplified version of Multi-Layer-Perceptrons. The BNN has binary connection parameters and can realize a desired Boolean function provided a sufficient number of hidden neurons are given. As an application, we use rules of Binary Cellular Autornata (BCAs) as teacher signals. Our elemental learning algorithm is based on random search of the binary parameters. In basic neurnerical experiments, we have investigated approximation property for the number of hidden neurons and have confirmed efficiency of the algorithm. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | Binary Neural networks / Binary Cellular Automaton / hidden neurons / supervised learning |
Paper # | NC2006-202 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2007/3/9(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 | Neurocomputing (NC) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | Learning of CA rules by Digital Multi-Layer-Perceptrons |
Sub Title (in English) | |
Keyword(1) | Binary Neural networks |
Keyword(2) | Binary Cellular Automaton |
Keyword(3) | hidden neurons |
Keyword(4) | supervised learning |
1st Author's Name | Toru ABE |
1st Author's Affiliation | Department of electronics, Electrical and Computer Engineering, Hosei University() |
2nd Author's Name | Toshimichi SAITO |
2nd Author's Affiliation | Department of electronics, Electrical and Computer Engineering, Hosei University |
Date | 2007-03-16 |
Paper # | NC2006-202 |
Volume (vol) | vol.106 |
Number (no) | 590 |
Page | pp.pp.- |
#Pages | 5 |
Date of Issue |