Accession Number:

ADD020083

Title:

Neural Network Function Classifier

Descriptive Note:

Patent Application, Filed 7 Feb 2003

Corporate Author:

DEPARTMENT OF THE NAVY WASHINGTON DC

Personal Author(s):

Report Date:

2003-02-07

Pagination or Media Count:

13.0

Abstract:

A method and a system for determining a best function for representing a data set. The method includes providing a classifier having a plurality of neural network sets. Each of the neural networks in a particular set is trained to recognize a particular data set type. The best function representation of the data set is determined from the neural network output. The system comprises sets of trained neural networks having neural networks trained to identify different types of data. The number of neural networks within each neural network set will depend on the number of function types that are represented. The system further comprises an aide for determining based on the best function representation of the data set.

Subject Categories:

  • Computer Systems
  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE