Accession Number:

ADA270209

Title:

Statistical Learning Theory and Algorithms

Descriptive Note:

Final rept. 15 Feb 92-14 Feb 93,

Corporate Author:

YALE UNIV NEW HAVEN CT DEPT OF COMPUTER SCIENCE

Personal Author(s):

Report Date:

1993-02-14

Pagination or Media Count:

2.0

Abstract:

This project addressed three fundamental areas in statistical learning theory and algorithms 1 a practical and theoretically sound method or estimating generalization performance of nonlinear learning systems Generalized Prediction Error, GPE, 2 a more powerful and efficient class of network architectures Parameterized Projection Pursuit Regression P3R networks, and 3 faster real-time learning methods based on asymptotically optimal stochastic gradient search. Three papers were published under this grant. Additionally, a graduate student finished his PhD under research topic Networks with Learned Unit Response Functions .

Subject Categories:

  • Statistics and Probability

Distribution Statement:

APPROVED FOR PUBLIC RELEASE