High-Level Connectionist Models

Abstract

Standard methods for inducing both the structure and weight values of recurrent neural networks fit an assumed class of architectures to every task. This simplification is necessary because the interactions between network structure and function are not well understood. Evolutionary computation, which includes genetic algorithms and evolutionary programming, is a population-based search method that has shown promise in such complex tasks. This paper argues that genetic algorithms are inappropriate for network acquisition and describes an evolutionary program, called GNARL, that simultaneously acquires both the structure and weights for recurrent networks. This algorithm's empirical acquisition method allows for the emergence of complex behaviors and topologies that are potentially excluded by the artificial architectural constraints imposed in standard network induction methods.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Apr 01, 1993
Accession Number
ADA268680

Entities

People

  • Jordan B. Pollack

Organizations

  • Ohio State University

Tags

Communities of Interest

  • Energy and Power Technologies

DTIC Thesaurus Topics

  • Algorithms
  • Artificial Intelligence
  • Cognitive Science
  • Computational Science
  • Computer Programming
  • Computer Simulations
  • Computers
  • Control Systems
  • Evolutionary Algorithms
  • Genetic Algorithms
  • Information Science
  • Language
  • Mathematical Models
  • Neural Networks
  • Psychology
  • Topology
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Artificial Intelligence
  • Neural Network Machine Learning.

Technology Areas

  • AI & ML
  • AI & ML - Machine Learning Algorithms
  • AI & ML - Neural Networks
  • Biotechnology