Accession Number:

ADA270136

Title:

Using Neural Networks for Underwater Target Ranging

Descriptive Note:

Corporate Author:

MATERIALS RESEARCH LABS ASCOT VALE (AUSTRALIA)

Personal Author(s):

Report Date:

1993-01-01

Pagination or Media Count:

6.0

Abstract:

Underwater weapons often have to range their range their targets from complex and highly variable signals, referred to as signatures. If artificial neural networks are applied to this task, the complexity of the ranging problem demands the use of networks with relatively large internal structures. This paper discusses the application of layered, feed-forward networks learning by back-propagation Rumelhart networks to this problem. The work discussed demonstrates that these networks may have improved generalisation by using noise added to the training set

Subject Categories:

  • Underwater Ordnance

Distribution Statement:

APPROVED FOR PUBLIC RELEASE