Selective Learning Algorithm for Certain Types of Learning Failure in Multilayer Perceptrons

Abstract

A simple selective learning algorithm for use with Multilayer Perceptrons (MLPs) is presented. This algorithm has proved useful in certain types of problems where learning failure occurs using standard back propagation. Examples of these problems are included. The algorithm is based on the rms output error, computed across all output nodes and all training patterns. The learning rate is decreased for all individual output nodes each time the error is less than a user chosen multiple of the rms error corresponding to the previous pass. This algorithm has produced convergence where the standard fixed gain back propagation failed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1990
Accession Number
ADA223982

Entities

People

  • George Rogers
  • Jeffrey L. Solka

Organizations

  • Naval Surface Warfare Center

Tags

Communities of Interest

  • Weapons Technologies

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Convergence
  • Data Processing
  • Data Sets
  • Engineering
  • Expert Systems
  • Information Operations
  • Learning
  • Mathematics
  • Radar Signals
  • Signal Processing
  • Standards
  • Surface Warfare
  • Training
  • Transfer Functions
  • Warfare

Fields of Study

  • Computer science

Readers

  • Computational Modeling and Simulation
  • Mathematics or Statistics
  • Neural Network Machine Learning.