Accession Number:

ADA279343

Title:

Determining Neural Network Hidden Layer Size Using Evolutionary Programming

Descriptive Note:

Corporate Author:

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

Personal Author(s):

• McDonnell, John R.
• Waagen, Don

Report Date:

1993-01-01

Pagination or Media Count:

6.0

Abstract:

This work investigates the application of evolutionary programming, a stochastic search technique, for simultaneously determining the weights and the number of hidden units in a fully-connected, multi-layer neural network. The simulated evolution search paradigm provides a means for optimizing both network structure and weight coefficients. Orthogonal learning is implemented by independently modifying network structure and weight parameters. Different structural level search strategies are investigated by comparing the training processes for the 3-bit parity problem. The results indicate that evolutionary programming provides a robust framework for evolving neural networks.

Descriptors:

• *NEURAL NETS
• *COMPUTER PROGRAMMING
• REPRINTS
• STOCHASTIC PROCESSES
• DETECTION
• COEFFICIENTS
• WEIGHT
• LEARNING
• PARITY
• COMPUTER NETWORKS
• SIGNALS
• STRATEGY
• TRAINING
• LAYERS
• PARAMETERS

Subject Categories:

• Operations Research
• Computer Systems

Distribution Statement:

APPROVED FOR PUBLIC RELEASE