Abstract:
Gradient descent techniques such as backpropagation have been used effectively to train neural network connection weights; however, in some applications gradient informat...Show MoreMetadata
Abstract:
Gradient descent techniques such as backpropagation have been used effectively to train neural network connection weights; however, in some applications gradient information may not be available. Biologically inspired genetic algorithms provide an alternative. The paper explores an approach in which a traditional genetic algorithm using standard two-point crossover and mutation is applied within the cascade-correlation learning architecture to train neural network connection weights. In the cascade-correlation architecture the hidden unit feature detector mapping is static; therefore, the possibility of the crossover operator shifting genetic material out of its useful context is reduced.<>
Published in: [Proceedings] COGANN-92: International Workshop on Combinations of Genetic Algorithms and Neural Networks
Date of Conference: 06-06 June 1992
Date Added to IEEE Xplore: 06 August 2002
Print ISBN:0-8186-2787-5