论文信息 - A mixed genetic approach to the optimization of neural controllers

A mixed genetic approach to the optimization of neural controllers

The author discusses some of the capabilities of genetic algorithms (GAs). GAs are compared with other standard optimization methods like gradient descent or simulated annealing (SA). It is shown that SA is just a special case of GA. The role of a population in the optimization process is demonstrated by an example. GA was applied as a learning algorithm to neural networks.<<ETX>>

J. Heistermann | J. Heistermann | Jochen Heistermann

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

[2] N. Metropolis,et al. Equation of State Calculations by Fast Computing Machines , 1953, Resonance.

[3] Klaus Waldschmidt,et al. Der assoziative Universalprozessor AM3: Architektur, Befehlssatz und objekt-orientiertes Programmierinterface , 1992, ARCS.

[4] John H. Holland,et al. Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[5] A. H. Gill. The Industrial and Artistic Technology of Paint and Varnish , 1904 .

[6] C. D. Gelatt,et al. Optimization by Simulated Annealing , 1983, Science.

[7] Jochen Heistermann. A parallel hybrid learning approach to artificial neural nets , 1991, Proceedings of the Third IEEE Symposium on Parallel and Distributed Processing.