论文信息 - Evolutionary Structuring of Neural Networks by Solving a Binary Problem

Evolutionary Structuring of Neural Networks by Solving a Binary Problem

We present an Evolutionary Algorithm to solve special kinds of binary optimization tasks: block-structured pseudo-Boolean problems. The Evolutionary Algorithm uses a parametric neighbourhood model, and performs an adaptive, problem-adequate neighbourhood search. We consider the solution of block-structured pseudo-Boolean problems as one part of the structure design for neural networks. The performance of our approach is demonstrated on an illustrative structuring problem.

J. Born | I. Santibáñez-Koref

[1] K. Lang,et al. Learning to tell two spirals apart , 1988 .

[2] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[3] W. Vent,et al. Rechenberg, Ingo, Evolutionsstrategie — Optimierung technischer Systeme nach Prinzipien der biologischen Evolution. 170 S. mit 36 Abb. Frommann‐Holzboog‐Verlag. Stuttgart 1973. Broschiert , 1975 .

[4] Ingo Rechenberg,et al. Evolutionsstrategie : Optimierung technischer Systeme nach Prinzipien der biologischen Evolution , 1973 .

[5] Hiroaki Kitano,et al. Designing Neural Networks Using Genetic Algorithms with Graph Generation System , 1990, Complex Syst..

[6] Joachim Born,et al. Designing Neural Networks by Adaptively Building Blocks in Cascades , 1994, PPSN.

[7] Hans-Paul Schwefel,et al. Numerical Optimization of Computer Models , 1982 .