Learning chaotic dynamics under noise with on-line EM algorithm

被引：0

作者：

Yoshida, Wako ^{[1
]}

Ishii, Shin ^{[1
,2
]}

Sato, Masa-Aki ^{[2
]}

机构：

[1] Graduate School of Information Science, Nara Institute of Science and Technology, Ikoma, 630-0101, Japan

[2] ATR Human Information Processing Research Laboratories, Kyoto, 619-0288, Japan

来源：

Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi) | 2001年 / 84卷 / 06期

关键词：

Algorithms - Learning systems - Neural networks - Online systems - Spurious signal noise;

D O I：

10.1002/1520-6440(200106)84:63.0.CO;2-7

中图分类号：

学科分类号：

摘要：

In this article, we discuss the learning of chaotic dynamics by using a normalized Gaussian network (NGnet). The NGnet is trained by an on-line EM algorithm in order to learn the vector field of the chaotic dynamics. We also investigate the robustness of our approach to two kinds of noise processes: system noise and observation noise. It is shown that the trained NGnet is able to reproduce a chaotic attractor, even under the two kinds of noise. The trained NGnet also shows good prediction performance. When only part of the dynamical variables are observed, the NGnet is trained to learn the vector field in the delay coordinate space. It is shown that the chaotic dynamics is able to be learned with this method under the two kinds of noise. © 2001 Scripta Technica.

引用

页码：23 / 31

共 50 条

[1] Learning chaotic dynamics under noise with on-line EM algorithm
Yoshida, W
Ishii, S
Sato, MA
[J]. ELECTRONICS AND COMMUNICATIONS IN JAPAN PART III-FUNDAMENTAL ELECTRONIC SCIENCE, 2001, 84 (06): : 23 - 31
[2] On-line EM algorithm and reconstruction of chaotic dynamics
Ishii, S
Sato, M
[J]. NEURAL NETWORKS FOR SIGNAL PROCESSING VIII, 1998, : 360 - 369
[3] Reconstruction of chaotic dynamics by on-line EM algorithm
Ishii, S
Sato, MA
[J]. NEURAL NETWORKS, 2001, 14 (09) : 1239 - 1256
[4] Reinforcement learning based on on-line EM algorithm
Sato, M
Ishii, S
[J]. ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 11, 1999, 11 : 1052 - 1058
[5] On-line learning with malicious noise and the closure algorithm
Auer, P
Cesa-Bianchi, N
[J]. ANNALS OF MATHEMATICS AND ARTIFICIAL INTELLIGENCE, 1998, 23 (1-2) : 83 - 99
[6] On-line learning with malicious noise and the closure algorithm
Peter Auer
Nicolò Cesa-Bianchi
[J]. Annals of Mathematics and Artificial Intelligence, 1998, 23 : 83 - 99
[7] On-line EM reinforcement learning
Yoshimoto, J
Ishii, S
Sato, M
[J]. IJCNN 2000: PROCEEDINGS OF THE IEEE-INNS-ENNS INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS, VOL III, 2000, : 163 - 168
[8] On-line EM algorithm for mixture of local experts
Sato, M
Ishii, S
[J]. ICONIP'98: THE FIFTH INTERNATIONAL CONFERENCE ON NEURAL INFORMATION PROCESSING JOINTLY WITH JNNS'98: THE 1998 ANNUAL CONFERENCE OF THE JAPANESE NEURAL NETWORK SOCIETY - PROCEEDINGS, VOLS 1-3, 1998, : 1397 - 1401
[9] On-line EM algorithm for the normalized gaussian network
Sato, M
Ishii, S
[J]. NEURAL COMPUTATION, 2000, 12 (02) : 407 - 432
[10] Dynamics of on-line competitive learning
Biehl, M
Freking, A
Reents, G
[J]. EUROPHYSICS LETTERS, 1997, 38 (01): : 73 - 78

← 1 2 3 4 5 →