A Sum Rule Satisfied by Optimised Feed-Forward Layered Networks

Abstract

Take a feed-forward layered network (such as a multilayer perceptron or a radial basis function network) which is to operate as a pattern classifier. The network may have several hidden layers, as many nodes as required and any desired nonlinearities on the hidden units. The transfer functions of the output nodes should be linear. If the network is trained (using any appropriate problem) to minimise the sum squared error over all outputs and patterns such that the output weights have minimum norm, then the output values of the trained network for any subsequent input pattern will sum to a constant. keywords: Radar, Great Britain.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 24, 1989
Accession Number
ADA220767

Entities

People

  • A. R. Webb
  • D. Lowe
  • D. S. Broomhead

Organizations

  • Royal Signals and Radar Establishment

Tags

DTIC Thesaurus Topics

  • Coding
  • Copyrights
  • Education
  • Equations
  • Executives
  • Intellectual Property
  • Iterations
  • Literature
  • Machine Learning
  • Mathematics
  • Notation
  • Observation
  • Optimization
  • Pattern Recognition
  • Recognition
  • Training
  • Transfer Functions

Readers

  • Neural Network Machine Learning.
  • Phased Array Antenna Design.
  • Systems Analysis and Design