| Presentation | 2003/5/1 Association Property of an Inverse Delayed Neural Network Hongge Li, Shunsuke Akimoto, Yoshihiro Hayakawa, Shigeo Sato, Koji Nakajima, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | At present, the development of artificial neural network has obtained the satisfying success. Many models of neural network have been proposed and investigated. We have recently proposed a novel neuron model in a critical state. Theoretical investigations explain that the neuron of Inverse Delayed model has the advantage than conventional neuron models. In order to further discuss the fundamental characteristics of Inverse Delayed model, in the present study, we carry out the numerical experiment of storage capacity and dynamic behaviours on the ID model (Inverse Delayed Model) in detail. In order to compare the simulation results, we simulate the different neural network models separately including the Hopfield model, ID model and non-negative resistance ID model in the same condition. We further confirm the property of ID model through the simulation results. At last, we introduce an architecture of hardware that can be realized with stochastic logic. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Neural Network / ID model / Negative Resistance / Capacity / stochastic logic |
| Paper # | NLP2003-4 |
| Date of Issue |
| Conference Information | |
| Committee | NLP |
|---|---|
| Conference Date | 2003/5/1(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 | ENG |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Association Property of an Inverse Delayed Neural Network |
| Sub Title (in English) | |
| Keyword(1) | Neural Network |
| Keyword(2) | ID model |
| Keyword(3) | Negative Resistance |
| Keyword(4) | Capacity |
| Keyword(5) | stochastic logic |
| 1st Author's Name | Hongge Li |
| 1st Author's Affiliation | Research Institute of Electrical Communication, Tohoku University() |
| 2nd Author's Name | Shunsuke Akimoto |
| 2nd Author's Affiliation | Research Institute of Electrical Communication, Tohoku University |
| 3rd Author's Name | Yoshihiro Hayakawa |
| 3rd Author's Affiliation | Research Institute of Electrical Communication, Tohoku University |
| 4th Author's Name | Shigeo Sato |
| 4th Author's Affiliation | Research Institute of Electrical Communication, Tohoku University |
| 5th Author's Name | Koji Nakajima |
| 5th Author's Affiliation | Research Institute of Electrical Communication, Tohoku University |
| Date | 2003/5/1 |
| Paper # | NLP2003-4 |
| Volume (vol) | vol.103 |
| Number (no) | 37 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |