Complexity control method for recurrent neural networks

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper demonstrates that the Lyapunov exponents of recurrent neural networks can be controlled by our proposed methods. One of the control methods minimize a squared error e λ = (λ - λ obj) 2/2 by a gradient method, where λ is the largest Lyapunov exponent of the network and λ obj is a desired exponent. λ implying the dynamical complexity is calculated by observing the state transition for a long-term period. This method is, however, computationally expensive for large-scale recurrent networks and the control is unstable for recurrent networks with chaotic dynamics since a gradient correction through time diverges due to the chaotic instability. We also propose an approximation method in order to reduce the computational cost and realize a 'stable' control for chaotic networks. The new method is based on a stochastic relation which allows us to calculate the correction through time in a fashion without time evolution. Simulation results show that the approximation method can control the exponent for recurrent networks with chaotic dynamics under a restriction.

Original languageEnglish
Title of host publicationProceedings of the IEEE International Conference on Systems, Man and Cybernetics
PublisherIEEE
Volume1
Publication statusPublished - 1999
Event1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics' - Tokyo, Jpn
Duration: 1999 Oct 121999 Oct 15

Other

Other1999 IEEE International Conference on Systems, Man, and Cybernetics 'Human Communication and Cybernetics'
CityTokyo, Jpn
Period99/10/1299/10/15

ASJC Scopus subject areas

  • Hardware and Architecture
  • Control and Systems Engineering

Fingerprint Dive into the research topics of 'Complexity control method for recurrent neural networks'. Together they form a unique fingerprint.

  • Cite this

    Sakai, M., Honma, N., & Abe, K. (1999). Complexity control method for recurrent neural networks. In Proceedings of the IEEE International Conference on Systems, Man and Cybernetics (Vol. 1). IEEE.