Multilayer Piecewise Linear Networks. Revision 1.

Abstract

Feed-forward layered networks are the simplest neural computers. These networks provide fast compact devices for computing discriminant functions and other mappings applicable to pattern recognition problems. This report treats the problem of weight initialization/assignment for feed-forward networks with piecewise linear neuron transfer function. Specific transformations are shown to be impossible with a single hidden layer. Techniques are presented for constructing such transformations with two hidden layers.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Nov 01, 1994
Accession Number
ADA289885

Entities

People

  • W. O. Alltop

Organizations

  • Naval Air Warfare Center Weapons Division

Tags

Communities of Interest

  • C4I
  • Weapons Technologies

DTIC Thesaurus Topics

  • Aerial Warfare
  • Boundaries
  • Computing Devices
  • Convex Sets
  • Decomposition
  • Geometry
  • Guarantees
  • Image Processing
  • Neural Networks
  • Numbers
  • Pattern Recognition
  • Real Numbers
  • Recognition
  • Security
  • Transfer Functions
  • Triangles
  • Two Dimensional

Fields of Study

  • Computer science

Readers

  • Adaptive Control and Estimation with Uncertainty in Dynamic Systems.
  • Neural Network Machine Learning.

Technology Areas

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