この論文をさがす
抄録
Universal Learning Network (ULN) is proposed and its application to chaos control are discussed. ULNs form a super-set of neural networks. They consist of a number of inter-connected nodes where the nodes may have any continuously differentiable nonlinear functions in them and each pair of nodes can be connected by multiple branches with arbitrary (positive, zero, or even negative) time delays. A generalized learning algorithm is derived for the ULNs, in which both the first ordered derivatives (gradients) and the higher ordered derivatives are incorporated. The derivatives are calculated by using forward or backward propagation scheme. The algorithm can also be used in a unified manner for almost all kinds of learning networks. As an application of ULNs, a chaos control method using maximum Lyapunov number of ULNs is proposed . The maximum Lyapunov number of ULNs can be formulated by using higher ordered derivatives of ULNs and parameters of ULNs can be adjusted for the maximum Lyapunov number to approach the target value. From simulation results, it has been shown that a fully connected ULN with three nodes is able to display chaotic behaviors.
収録刊行物
-
- 九州大学大学院システム情報科学紀要
-
九州大学大学院システム情報科学紀要 4 (1), 13-27, 1999-03-26
九州大学大学院システム情報科学研究科
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390572174796933248
-
- NII論文ID
- 110000579903
-
- NII書誌ID
- AN10569524
-
- DOI
- 10.15017/1498416
-
- ISSN
- 21880891
- 13423819
-
- HANDLE
- 2324/1498416
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- IRDB
- CiNii Articles
-
- 抄録ライセンスフラグ
- 使用可