| Presentation | 2017-11-05 Reconstructing Bifurcation Diagrams of Chaotic neuron Using Extreme Learning Machine Yoshitaka Itoh, Masaharu Adachi, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | In recent year, an extreme learning machine which is simple structure have been applied to various problems. As one of the application examples, we have reconstructed bifurcation diagrams using the extreme learning machine. In the reconstruction of bifurcation diagram, we train extreme learning machine to model the time-series data sets which are generated by a dynamical system with different parameters. We assume that the higher prediction accuracy the time series predictors is, the higher reconstruction accuracy we obtain. However, we confirm that the extreme learning machine can not train to model time-series data sets that are generated by chaotic neuron model. In this paper, we show that an extreme learning machine with valiable ranges for synaptic weights of hidden neurons can train to model the time-series data sets of the chaotic neuron model. In addition, we show results of numerical experiments for the reconstruction of bifurcation diagram of the chaotic neuron model. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | reconstruction of bifurcation diagram / time series predictor / chaotic neuron / extreme learning machine |
| Paper # | NLP2017-74 |
| Date of Issue | 2017-10-29 (NLP) |
| Conference Information | |
| Committee | NLP |
|---|---|
| Conference Date | 2017/11/5(2days) |
| Place (in Japanese) | (See Japanese page) |
| Place (in English) | Research Institute of Electrical Communication Tohoku University |
| Topics (in Japanese) | (See Japanese page) |
| Topics (in English) | Applications of nonlinear complex systems theory to existing nonlinear complex real-systems, etc |
| Chair | Masaharu Adachi(Tokyo Denki Univ.) |
| Vice Chair | Norikazu Takahashi(Okayama Univ.) |
| Secretary | Norikazu Takahashi(Nagaoka Univ. of Tech.) |
| Assistant | Toshihiro Tachibana(Shonan Inst. of Tech.) / Masayuki Kimura(Kyoto Univ.) |
| Paper Information | |
| Registration To | Technical Committee on Nonlinear Problems |
|---|---|
| Language | JPN |
| Title (in Japanese) | (See Japanese page) |
| Sub Title (in Japanese) | (See Japanese page) |
| Title (in English) | Reconstructing Bifurcation Diagrams of Chaotic neuron Using Extreme Learning Machine |
| Sub Title (in English) | |
| Keyword(1) | reconstruction of bifurcation diagram |
| Keyword(2) | time series predictor |
| Keyword(3) | chaotic neuron |
| Keyword(4) | extreme learning machine |
| 1st Author's Name | Yoshitaka Itoh |
| 1st Author's Affiliation | Tokyo Denki University(Tokyo Denki Univ.) |
| 2nd Author's Name | Masaharu Adachi |
| 2nd Author's Affiliation | Tokyo Denki University(Tokyo Denki Univ.) |
| Date | 2017-11-05 |
| Paper # | NLP2017-74 |
| Volume (vol) | vol.117 |
| Number (no) | NLP-272 |
| Page | pp.pp.53-58(NLP), |
| #Pages | 6 |
| Date of Issue | 2017-10-29 (NLP) |