Determining Neural Network Hidden Layer Size Using Evolutionary Programming

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.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1993
Accession Number
ADA279343

Entities

People

  • Don Waagen
  • John R. Mcdonnell

Organizations

  • Naval Command, Control and Ocean Surveillance Center

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Algorithms
  • Coefficients
  • Computer Programming
  • Computing System Architectures
  • Congress
  • Convergence
  • Demographic Cohorts
  • Education
  • Mutations
  • Neural Networks
  • Ocean Surveillance
  • Optimization
  • Personal Information Managers
  • Probability
  • Random Variables
  • Standards
  • Training

Fields of Study

  • Computer science

Readers

  • Neural Network Machine Learning.
  • Operations Research

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks