Accession Number : ADA266853


Title :   Determining Neural Network Connectivity Using Evolutionary Programming


Corporate Author : NAVAL COMMAND CONTROL AND OCEAN SURVEILLANCE CENTER RDT AND E DIV SAN DIEGO CA


Personal Author(s) : McDonnell, John R ; Waagen, Don


Full Text : https://apps.dtic.mil/dtic/tr/fulltext/u2/a266853.pdf


Report Date : Mar 1993


Pagination or Media Count : 8


Abstract : This work investigates the application of evolutionary programming, a stochastic search technique, for determining connectivity in feedforward neural networks. The method is capable of simultaneously evolving both the connection scheme and the network weights. The number of synapses are incorporated into an objective function so that network parameter optimization is done with respect to a connectivity cost as well as mean pattern error. Experimental results are shown using feedforward networks for simple binary mapping problems.


Descriptors :   *NEURAL NETS , *STOCHASTIC PROCESSES , *COMPUTER PROGRAMMING , COMPUTER PROGRAMS , ALGORITHMS , SIGNAL PROCESSING , SIGNALS , WEIGHT , HEURISTIC METHODS , SYNAPSE , NUMBERS , MAPPING , PATTERNS , ERRORS , COMPUTER ARCHITECTURE , PARAMETERS , OPTIMIZATION , SOFTWARE ENGINEERING , FUNCTIONS


Subject Categories : Computer Programming and Software


Distribution Statement : APPROVED FOR PUBLIC RELEASE