Presentation | 2001/6/22 A Study of Generalization Ability of 3-Layer Recurrent Neural Networks Hiroshi NINOMIYA, Ayako SASAKI, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we study generalization ability of 3-layer recurrent neural networks(3LRNN). 3LRNN are composed of the both of the feed-forward the feedback connections. The generalization ability of 3LRNN is compared with one of 3-layer feed-forward neural networks through the computer simulations. It is shown that 3LRNN are not only almost equivalent to 3LFNN but also much superior to one on a certain condition from the viewpoint of the generalization capability. Furthermore, we investigate the generalization ability of 3LRNN with the neurons that have the step functions as the transfer functions. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | 3-layer recurrent neural networks / Feedback connections / Generalization ability |
Paper # | NC2001-31 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 2001/6/22(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 Study of Generalization Ability of 3-Layer Recurrent Neural Networks |
Sub Title (in English) | |
Keyword(1) | 3-layer recurrent neural networks |
Keyword(2) | Feedback connections |
Keyword(3) | Generalization ability |
1st Author's Name | Hiroshi NINOMIYA |
1st Author's Affiliation | Department of Information Science, Faculty of Engineering, Shonan Institute of Technology() |
2nd Author's Name | Ayako SASAKI |
2nd Author's Affiliation | Department of Information Science, Faculty of Engineering, Shonan Institute of Technology |
Date | 2001/6/22 |
Paper # | NC2001-31 |
Volume (vol) | vol.101 |
Number (no) | 154 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |