| Presentation | 1993/11/24 An Optimization Method of artificial Neural Networks based on a modified Information Sumio Watanabe, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | An optimization method of artificial neural networks is proposed based on a modified information criterion.To obtain the optimal model by an information criterion,in conventional methods,the maximum likelihood estimator is found for each model,and then information criteria are compared.The proposed method enables us to obtain the optimal model and parameters simultaneously by only one learning procedure.There are several theoretical problems to support the proposed method,so its effectiveness is verified by computer simulation. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Neural Network / Information Criterion / Expected Error / Statistical estimation / strncture optimization |
| Paper # | NC93-52 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 1993/11/24(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) | An Optimization Method of artificial Neural Networks based on a modified Information |
| Sub Title (in English) | |
| Keyword(1) | Neural Network |
| Keyword(2) | Information Criterion |
| Keyword(3) | Expected Error |
| Keyword(4) | Statistical estimation |
| Keyword(5) | strncture optimization |
| 1st Author's Name | Sumio Watanabe |
| 1st Author's Affiliation | Information and Communication R&D Center,RICOH() |
| Date | 1993/11/24 |
| Paper # | NC93-52 |
| Volume (vol) | vol.93 |
| Number (no) | 341 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |