Multilayer Perceptron Learning Via Genetic Search for Hidden Layer Activations

by

Hassoun, M., H. and Song, J.

Literature search on Evolutionary ComputationBBase ©1999-2013, Rasmus K. Ursem
     Home · Search · Adv. search · Authors · Login · Add entries   Webmaster
Note to authors: Please submit your bibliography and contact information - online papers are more frequently cited.

Info: Proceedings of the World Congress on Neural Networks (Conference proceedings), 1993, p. III437 - III444
Keywords:connectionism, genetic algorithms
Abstract:
ABSTRACT A new learning technique is proposed for multilayer neural networks based [NN] on genetic search, in hidden target space, and gradient descent learning strategies. Our simulations show that the new algorithm combines the global optimization [GO] capabilities of genetic algorithms [GA] with the speed of gradient descent local search [LS] in order to outperform pure descent-based algorithms such as backpropagation. In addition, we show that genetic search in hidden target space is less complex than that of weight space.
Internet search:Search Google
Search Google Scholar
Search Citeseer using Google
Search Google for PDF
Search Google Scholar for PDF
Search Citeseer for PDF using Google

Review item:

Mark as doublet (will be reviewed)

Print entry



BibTex:
@inproceedings{Hassoun93,
   key       = {connectionism, genetic algorithms},
   author    = {Mohamad H. Hassoun and Jing Song},
   title     = {Multilayer Perceptron Learning Via Genetic Search for
       Hidden Layer Activations},
   booktitle = {Proceedings of the World Congress on Neural Networks},
   organization = {WCNN93},
   year      = {1993},
   pages     = {III437 - III444},
   abstract  = {ABSTRACT
       A new learning technique is proposed for multilayer neural 
       networks based on genetic search, in hidden target space, and 
       gradient descent learning strategies. Our simulations show that 
       the new algorithm combines the global optimization capabilities 
       of genetic algorithms with the speed of gradient descent local 
       search in order to outperform pure descent-based algorithms such
       as backpropagation. In addition, we show that genetic search in 
       hidden target space is less complex than that of weight space.},
}