Gain Modification Enhances High Momentum Backward Propagation

Abstract

A backward propagation network is presented which simultaneously modifies the gain parameters and the synaptic weights. Gain modification is shown to enhance the improvement in convergence rate obtained by high momentum in standard synaptic backward propagation. These improvements occur without degrading the generalization capabilities of the final solutions obtained by the network. Keywords: Backward propagation; Gain modification; Momentum.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 08, 1989
Accession Number
ADA217733

Entities

People

  • Charles M. Bachmann

Organizations

  • Brown University

Tags

DTIC Thesaurus Topics

  • Algorithms
  • Convergence
  • Couplings
  • Data Sets
  • Differential Equations
  • Equations
  • Graphs
  • Military Research
  • Momentum
  • Network Architecture
  • Nonlinear Differential Equations
  • Notation
  • Simulations
  • Standards
  • Training
  • Vector Spaces

Readers

  • Electronics Engineering
  • Fluid Dynamics.
  • Neuroscience