Control of Nonlinear System by Multiplication and Combining Layer on Dynamic Neural Networks

동적 신경망의 층의 분열과 합성에 의한 비선형 시스템 제어

  • Published : 1999.04.01

Abstract

We propose an algorithm for obtaining the optimal node number of hidden units in dynamic neural networks. The dynamic nerual networks comprise of dynamic neural units and neural processor consisting of two dynamic neural units; one functioning as an excitatory neuron and the other as an inhibitory neuron. Starting out with basic network structure to solve the problem of control, we find optimal neural structure by multiplication and combining dynamic neural unit. Numerical examples are presented for nonlinear systems. Those case studies showed that the proposed is useful is practical sense.

Keywords

References

  1. The Journal of Intelligent and Fuzzy Systems v.1 Dynamic Neural Units With Applications to the Control of Unknown Nonlinear System M. M. Gupta;D. H. Rao
  2. 대한전기학회 논문지 v.45 no.12 상태변수 모형을 가진 동적 신경망을 이용한 비선형 시스템의 제어기 설계 서보혁;박성욱
  3. 대한전기학회 논문지 v.46 no.12 동적 신경망을 이용한 비선형 다변수 시스템의 제어기 설계 서보혁;박성욱
  4. IEEE Trans. Neural Networks v.5 no.6 Network Information Criterion-Determining the Number of Hidden Units for an Artificial Neural Network Model Murata, Yoshizawa;Amari
  5. IEEE Trans. Neural Networks v.2 no.5 An Information Criterion for Optimal Neural Network Selection D. B. Fogel
  6. IEEE Trans Neural Networks v.7 no.2 The Cascade-Correlation Learning: A Projection Pursuit Learning Perspective J. N. Hwang;S. S. You;S. R. Lay;I. C. Jou
  7. IEEE Trans. Neural Networks v.8 no.6 Structure Optimization of Neural Networks with the A -Algorithm Axel Doering;Miroslaw Galicki;Herbert Witte
  8. ICS Report 8901 Dynamic Node Creation in Backpropagation Networks T. Ash
  9. 計測自動制御學論 v.28 no.4 隱わュニツトの合成による階層型 ニュ-ラ ルネツトワ-クのコンペクト構造化 增田;藤井;池谷;相部
  10. Statistics for the social scientist v.1 Introducing statistics K. A. Yeomans