WEKO3
アイテム
Dynamical Singularities in Online Learning of Recurrent Neural Networks
http://hdl.handle.net/10445/6017
http://hdl.handle.net/10445/6017d2d4b0fb-0608-41d4-a5b0-bbcbc67e77a0
名前 / ファイル | ライセンス | アクション |
---|---|---|
![]() |
|
Item type | 会議発表論文 / Conference Paper(1) | |||||
---|---|---|---|---|---|---|
公開日 | 2011-04-18 | |||||
タイトル | ||||||
タイトル | Dynamical Singularities in Online Learning of Recurrent Neural Networks | |||||
言語 | ||||||
言語 | eng | |||||
資源タイプ | ||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_5794 | |||||
資源タイプ | conference paper | |||||
著者 |
Saito, Asaki
× Saito, Asaki× Taiji, Makoto× Ikegami, Takashi |
|||||
抄録 | ||||||
内容記述タイプ | Abstract | |||||
内容記述 | We numerically and theoretically demonstrate various singularities, as a dynamical system, of a simple online learning system of a recurrent neural network (RNN) where RNN performs the one-step prediction of a time series generated by a one-dimensional map. More specifically, we show first through numerical simulations that the learning system exhibits singular behaviors (“neutral behaviors”) different from ordinary chaos, such as almost zero finite-time Lyapunov exponents, as well as inaccessibility and power-law decay of the distribution of learning times (transient times). Also, we show through linear stability analysis that, as a dynamical system, the learning system is represented by a singular map whose Jacobian matrix has eigenvalue unity in the whole phase space. In particular, we state that the singularity as a dynamical system (shown by the second method) provides a basic reason for the neutral behaviors (shown by the first method) exhibited by the learning system. | |||||
書誌情報 |
Proceedings of the 2007 IEEE Symposium on Foundations of Computational Intelligence (FOCI 2007) p. 174-179, 発行日 2007 |
|||||
研究業績種別 | ||||||
値 | 国際会議/International Conference | |||||
単著共著 | ||||||
値 | 共著/joint | |||||
権利 | ||||||
権利情報 | (c) 2007 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works. | |||||
著者版フラグ | ||||||
出版タイプ | VoR | |||||
出版タイプResource | http://purl.org/coar/version/c_970fb48d4fbd8a85 | |||||
出版者 | ||||||
出版者 | IEEE |