Title :
Disruption analysis for neural network topology evolution systems
Author :
Dàvila, Jaime J.
Author_Institution :
Sch. of Cognitive Sci., Hampshire Coll., Amherst, MA, USA
Abstract :
This paper presents a method for analyzing GA effectiveness for the evolution of neural networks. The analysis is based on the schemata of the (phenotype) neural network being evolved, as opposed to the traditional method of analyzing schemata disruptions at the genotype level. Comparisons between the two types of analysis are made. Empirical data is presented that indicates the greater validity of the analysis at the phenotype level.
Keywords :
genetic algorithms; multilayer perceptrons; neural net architecture; topology; disruption analysis; genetic algorithms; hidden layers; multilayer network; neural network topology evolution systems; phenotype level; schemata disruptions; Algorithm design and analysis; Cellular neural networks; Cognitive science; Educational institutions; Genetic algorithms; Genetic mutations; Network topology; Neural networks; System testing;
Conference_Titel :
Neural Information Processing, 2002. ICONIP '02. Proceedings of the 9th International Conference on
Print_ISBN :
981-04-7524-1
DOI :
10.1109/ICONIP.2002.1199008
