Accession Number:

ADA277313

Title:

A Differential Theory of Learning for Efficient Statistical Pattern Recognition

Descriptive Note:

Final rept. 30 Sep 1989-29 Sep 1993

Corporate Author:

CARNEGIE-MELLON UNIV PITTSBURGH PA

Personal Author(s):

Report Date:

1993-12-15

Pagination or Media Count:

455.0

Abstract:

Probabilistic learning strategies currently use are inefficient, requiring high classifier complexity and large training samples. In this report, we introduce and analyze an asymptotically efficient differential learning strategy. It guarantees the best generalization allowed by the chosen classifier paradigm. Differential learning also requires the classifier with minimal complexity. The theory is demonstrated in several real-world machine learningpattern recognition tasks. Learning, Pattern recognition, Classification, Neural networks.

Subject Categories:

  • Statistics and Probability
  • Cybernetics

Distribution Statement:

APPROVED FOR PUBLIC RELEASE