Publication: Studying the capacity of cellular encoding to generate feedforward neural network topologies
Loading...
Identifiers
ISSN: 1098-7576
ISBN: 0-7803-8359-1
Publication date
2004-07
Defense date
Advisors
Tutors
Journal Title
Journal ISSN
Volume Title
Publisher
IEEE
Impact
Export
Abstract
Many methods to codify artificial neural networks have been developed to avoid the disadvantages of direct encoding schema, improving the search into the solution's space. A method to analyse how the search space is covered and how are the movements along search process applying genetic operators is needed in order to evaluate the different encoding strategies for multilayer perceptrons (MLP). In this paper, the generative capacity, this is how the search space is covered for a indirect scheme based on cellular systems, is studied. The capacity of the methods to cover the search space (topologies of MLP space) is compared with the direct encoding scheme.
Description
Proceeding of: IEEE International Joint Conference on Neural Networks, IJCNN 2004, Budapest, 25-29 July 2004
Keywords
Encoding, Feedforward neural nets, Multilayer perceptrons
Bibliographic citation
IEEE International Joint Conference on Neural Networks, IJCNN 2004, Budapest, 25-29 July 2004, vol. 1, p. 211-215