Journal of Institute of Control, Robotics and Systems (제어로봇시스템학회논문지)

Institute of Control, Robotics and Systems (제어로봇시스템학회)
권호 표지

A Study on an Artificial Neural Network Design using Evolutionary Programming

진화 프로그래밍 기법을 이용한 신경망의 자동설계에 관한 연구

  • 강신준 (연세대학교 전기공학과) ;
  • 고택범 (경주대학교 컴퓨터전자공학부) ;
  • 우천희 (연세대학교 전기공학과) ;
  • 이덕규 (연세대학교 전기공학과) ;
  • 우광방 (연세대학교 전기공학과)
  • Published : 1999.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a design method based on evolutionary programming for feedforward neural networks which have a single hidden layer is presented. By using an evolutionary programming, the network parameters such as the network structure, weight, slope of sigmoid functions and bias of nodes can be acquired simultaneously. To check the effectiveness of the suggested method, two numerical examples are examined. The performance of the identified network is demonstrated.

Keywords

References

  1. Genetic Algorithms in Search, Optimization and Machine Learning D.E.Goldberg
  2. IEEE Trans. Evolutionary Computation v.1 no.1 Evolutionary computation : Comments on the history and current state T.Back;U.Hammel;H.P.Schwefel
  3. IEEE Trans. Neural Networks v.5 no.1 Genetic evolution of the topology and weight distribution of neural networks V.Maniezzo
  4. IEEE Trans. Neural Networks v.8 no.3 A new ecolutionary system for evolving artificial neural networks X.Yao
  5. Artificial Intelligence in Engineering Neural network design based on evolutionary programming J.Fang;Yugeng Xi
  6. IEEE Trans. Evolutionary Computation v.1 no.1 Evolving artifical neural networks to combine financial forecasts P.G.Harrald;M.Kamstra
  7. IEEE Trans. Neural Networks v.5 no.1 An evoltionary algorithm that constructs recurrent neural networks P.J.Angeline;G.M.Saunders;J.B.Pollack
  8. IEEE Trans. SMC v.26 no.2 Hybrid methods using genetic algorithms for global optimization J.M.Renders;S.P.Flasse
  9. Fuzzy and Neural Approaches in Engineering L.H.Tsoukalas;R.E.Uhrig