 |
    |
Central Point Crossover for Neuro-genetic Hybrids
Soonchul Jung and Byung-Ro Moon
School of Computer Science and Engineering, Seoul National University, Shillim-dong, Kwanak-gu, Seoul, 151-742 Koreasamuel@soar.snu.ac.kr
moon@soar.snu.ac.kr
Abstract. In this paper, we consider each neural network as a point in a multi-dimensional problem space and suggest a crossover that locates the central point of a number of neural networks. By this, genetic algorithms can spend more time around attractive areas. We also apply representational normalization to neural networks to maintain genotype consistency in crossover. For the normalization, we utilize the Hungarian method of matching problems. The experimental results of our neuro-genetic algorithm overall showed better performance over the traditional multi-start heuristic and the genetic algorithm with a traditional crossover. These results are evidence that it is attractive to exploit central areas of local optima.
LNCS 3102, p. 1292 ff.
lncs@springer.de
© Springer-Verlag Berlin Heidelberg 2004