Title :
Genetic algorithm for artificial neurogenesis
Author :
Clergue, Manuel ; COLLARD, Philippe
Author_Institution :
13S Lab., Valbonne, France
Abstract :
The paper presents a neurogenesis process based on the protein regulation system. The novelty is in applying some genetic algorithm work with neurogenesis, in particular work on genetic operators and work on fitness landscapes. In order to get relevant tests with reduced simulation costs, neurogenesis is applied to a well know problem, the cart-pole system, then results are commented
Keywords :
genetic algorithms; neural nets; simulation; artificial neurogenesis; cart-pole system; fitness landscapes; genetic algorithm; genetic operators; protein regulation system; reduced simulation costs; relevant tests; Biological cells; Costs; Encoding; Genetic algorithms; Network synthesis; Neural networks; Neurons; Production; Proteins; System testing;
Conference_Titel :
Evolutionary Computation Proceedings, 1998. IEEE World Congress on Computational Intelligence., The 1998 IEEE International Conference on
Conference_Location :
Anchorage, AK
Print_ISBN :
0-7803-4869-9
DOI :
10.1109/ICEC.1998.699790
