Multilayer Piecewise Linear Networks.
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. Neural networks, Pattern recognition, Geometry
Document Details
- Document Type
- Technical Report
- Publication Date
- Sep 01, 1994
- Accession Number
- ADA285382
Entities
People
- W. O. Alltop
Organizations
- Naval Air Warfare Center Weapons Division