Accession Number:

ADA265031

Title:

Piecewise Linear Neural Networks

Descriptive Note:

Interim rept. 1991-1992

Corporate Author:

NAVAL AIR WARFARE CENTER WEAPONS DIV CHINA LAKE CA

Personal Author(s):

Report Date:

1992-08-01

Pagination or Media Count:

24.0

Abstract:

Modern weapons systems often require pattern recognition devices and algorithms. The three-layer neural network--consisting of input layer, hidden layer, and output layer--has great potential as a pattern classifier. Determining the size of the hidden layer and computing the weights are two of the primary design as a function of the input and output dimensions and of the number of pattern prototypes. The neurons are assumed to have piecewise linear transfer functions.

Subject Categories:

  • Cybernetics
  • Target Direction, Range and Position Finding

Distribution Statement:

APPROVED FOR PUBLIC RELEASE