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.
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