| Presentation | 2002/1/22 Model Selection and Local Optimality in Learning Dynamical Systems using Recurrent Neural Networks Toshiharu YOKOYAMA, Ken-ichi TAKESHIMA, Ryohei NAKANO, |
|---|---|
| PDF Download Page | PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | We consider learning a dynamical system (DS) by a continuous-time recurrent neural network (RNN). An affine RNN (A-RNN), whose hidden units are linearly related to visible ones, is defined so that it always produces a DS.Learning a DS by an A-RNN is performed as a three-layer perceptron. This paper investigates model selection and local optima problem in the learning. The experiments showed that model selection cant be exactly done by monitoring generalization performance and in the learning there exist much more local optima than expected. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Recurrent neural networks / Dynamical system learning / Hidden unit / Affine neural dynamical system |
| Paper # | |
| Date of Issue |
| Conference Information | |
| Committee | NC |
|---|---|
| Conference Date | 2002/1/22(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) | Model Selection and Local Optimality in Learning Dynamical Systems using Recurrent Neural Networks |
| Sub Title (in English) | |
| Keyword(1) | Recurrent neural networks |
| Keyword(2) | Dynamical system learning |
| Keyword(3) | Hidden unit |
| Keyword(4) | Affine neural dynamical system |
| 1st Author's Name | Toshiharu YOKOYAMA |
| 1st Author's Affiliation | Department of Intelligence and Computer Science, Nagoya Institute of Technology() |
| 2nd Author's Name | Ken-ichi TAKESHIMA |
| 2nd Author's Affiliation | Department of Intelligence and Computer Science, Nagoya Institute of Technology |
| 3rd Author's Name | Ryohei NAKANO |
| 3rd Author's Affiliation | Department of Intelligence and Computer Science, Nagoya Institute of Technology |
| Date | 2002/1/22 |
| Paper # | |
| Volume (vol) | vol.101 |
| Number (no) | 616 |
| Page | pp.pp.- |
| #Pages | 7 |
| Date of Issue | |