Proceedings of the KIEE Conference (대한전기학회:학술대회논문집)

The Korean Institute of Electrical Engineers (대한전기학회)
권호 표지

A Learning Strategy for Neural Networks based on Evolutionary Algorithm

진화 알고리즘에 근거한 신경회로망 학습법

  • Mun, K.J. (Dept. of Electrical Engineering, Pusan National University) ;
  • Hwang, G.H. (Dept. of Electrical Engineering, Pusan National University) ;
  • Yang, S.O. (Dept. of Electrical Engineering, Pusan National University) ;
  • Lee, H.S. (Dept. of Electrical Engineering, Pusan National University) ;
  • Park, J.H. (Dept. of Electrical Engineering, Pusan National University)
  • Published : 1994.11.18
Download PDF
⟨ Previous Next ⟩

Abstract

This Paper Presents a learning strategy for neural networks based on genetic algorithms and evolution strategies. Genetic algorithms and evolution strategies are used to train weights of feedforward neural network to solve problems faster than neural network, especially backpropagation. Simulations are performed exclusive-OR problem, full-adder problem, sine function generator to demonstrate the effectiveness of neural-GA-ES.

Keywords