Presentation | 1996/5/24 Learning Dynamical Systems Produced by Recurrent Neural Networks Masahiro KIMURA, Ryohei NAKANO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, the concept of a neural dynamical system is proposed to investigate mathematically the learning of a dynamical system by a recurrent neural network with hidden units. We present the conditions for our recurrent neural network to produce a neural dynamical system, and also discuss the possibility of identifying a neural dynamical system via the learning of its temporal trajectories. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | recurrent neural network / dynamical system / learning / hidden units / temporal trajectory |
Paper # | NC96-6 |
Date of Issue |
Conference Information | |
Committee | NC |
---|---|
Conference Date | 1996/5/24(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) | Learning Dynamical Systems Produced by Recurrent Neural Networks |
Sub Title (in English) | |
Keyword(1) | recurrent neural network |
Keyword(2) | dynamical system |
Keyword(3) | learning |
Keyword(4) | hidden units |
Keyword(5) | temporal trajectory |
1st Author's Name | Masahiro KIMURA |
1st Author's Affiliation | NTT Communication Science Laboratories() |
2nd Author's Name | Ryohei NAKANO |
2nd Author's Affiliation | NTT Communication Science Laboratories |
Date | 1996/5/24 |
Paper # | NC96-6 |
Volume (vol) | vol.96 |
Number (no) | 76 |
Page | pp.pp.- |
#Pages | 8 |
Date of Issue |