| Presentation | 1997/2/6 A Comparison of Laplacian Prior and Gaussian Prior for Hierarchical Bayes Learning in Neural Nets Y. Chonan, T. Matsumoto, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | A hierarchical Bayes approach is taken in training Feedforward Neural Nets. Assuming Gaussian distribution and Laplacian distribution as prior probability of weight parameters, both models are evaluated by comparing their marginal likelihood. Simulation result shows marginal likelihood has close contacts with generalization ability. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Hierarchical Bayes Inference / Neural Net / Gaussian Prior / Laplacian Prior / Marginal Likelihood |
| Paper # | NLP96-132,NC96-86 |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 1997/2/6(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) | A Comparison of Laplacian Prior and Gaussian Prior for Hierarchical Bayes Learning in Neural Nets |
| Sub Title (in English) | |
| Keyword(1) | Hierarchical Bayes Inference |
| Keyword(2) | Neural Net |
| Keyword(3) | Gaussian Prior |
| Keyword(4) | Laplacian Prior |
| Keyword(5) | Marginal Likelihood |
| 1st Author's Name | Y. Chonan |
| 1st Author's Affiliation | Department of Electrical, Electronics and Computer Engineering, Waseda University() |
| 2nd Author's Name | T. Matsumoto |
| 2nd Author's Affiliation | Department of Electrical, Electronics and Computer Engineering, Waseda University |
| Date | 1997/2/6 |
| Paper # | NLP96-132,NC96-86 |
| Volume (vol) | vol.96 |
| Number (no) | 511 |
| Page | pp.pp.- |
| #Pages | 8 |
| Date of Issue | |