| Presentation | 2006-01-24 Synthesis of desired cellular automata based on binary neural networks Toshimichi SAITO, Takashi YAMAMICHI, Satoshi SUZUKI, Hiroyuki TORIKAI, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper considers analysis and synthesis of cellular automata (CAs). The CA has binary state variable and the dynamics is governed by a rule table : a kind of Boolean function. We realize the rule tables through binary neural networks (BNNs). The BNN has binary connection parameters and the learning algorithm is based upon the GA. First, we apply a rule table as teacher signals to BNN and investigate relation between complexity of the corresponding CA dynamics and the number of hidden neurons of the BNN. This investigation is basic for analysis of rich CA dynamics. Second, we try to reduce noise added to a spatio-temporal pattern of CA. Performing basic numerical experiments we can make the BNN to construct a desired rule table that gives the clear pattern. In the learning teacher signals are extracted with the majority principle from the noisy pattern. It may be developed into synthesis of desired CAs. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Supervised Learning / Cellular Automata / Binary Neural Networks / Genetic Algorithm |
| Paper # | NLP2005-119 |
| Date of Issue |
| Conference Information | |
| Committee | NLP |
|---|---|
| Conference Date | 2006/1/17(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) | Synthesis of desired cellular automata based on binary neural networks |
| Sub Title (in English) | |
| Keyword(1) | Supervised Learning |
| Keyword(2) | Cellular Automata |
| Keyword(3) | Binary Neural Networks |
| Keyword(4) | Genetic Algorithm |
| 1st Author's Name | Toshimichi SAITO |
| 1st Author's Affiliation | Department of Electronics, Electrical and Computer Engineering, Hosei University() |
| 2nd Author's Name | Takashi YAMAMICHI |
| 2nd Author's Affiliation | Department of Electronics, Electrical and Computer Engineering, Hosei University |
| 3rd Author's Name | Satoshi SUZUKI |
| 3rd Author's Affiliation | Department of Electronics, Electrical and Computer Engineering, Hosei University |
| 4th Author's Name | Hiroyuki TORIKAI |
| 4th Author's Affiliation | Department of Electronics, Electrical and Computer Engineering, Hosei University |
| Date | 2006-01-24 |
| Paper # | NLP2005-119 |
| Volume (vol) | vol.105 |
| Number (no) | 547 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |