| Presentation | 2010-10-29 On learning of dynamic binary neural networks Ryo ITOH, Toshimichi SAITO, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | This paper presents a dynamic binary neural network of N-bit binary sequence. Basically, the network is constructed by feedback of N-bit output to N-bit input. In order to approximate an objective teacher signal of binary sequence, we present a novel learing algorithm based on the genetic algorithm. Using an efficient initial cjromosome and hidden neuron share, we can reduce the number of hidden neurons and computation cost. Performing basic numerical experiment, the algorithm efficiency is confirmed. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Binary Neural networks (BNN) / Inverter / hydden neuron / Genetic algorithm (GA) |
| Paper # | NLP2010-94 |
| Date of Issue |
| Conference Information | |
| Committee | NLP |
|---|---|
| Conference Date | 2010/10/21(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) | On learning of dynamic binary neural networks |
| Sub Title (in English) | |
| Keyword(1) | Binary Neural networks (BNN) |
| Keyword(2) | Inverter |
| Keyword(3) | hydden neuron |
| Keyword(4) | Genetic algorithm (GA) |
| 1st Author's Name | Ryo ITOH |
| 1st Author's Affiliation | Department of Electrical and Electronics Engineering, Hosei University() |
| 2nd Author's Name | Toshimichi SAITO |
| 2nd Author's Affiliation | Department of Electrical and Electronics Engineering, Hosei University |
| Date | 2010-10-29 |
| Paper # | NLP2010-94 |
| Volume (vol) | vol.110 |
| Number (no) | 255 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |