Share Email Print

Proceedings Paper

How projection-pursuit learning works in high dimensions
Author(s): Ying Zhao; Christopher G. Atkeson
Format Member Price Non-Member Price
PDF $14.40 $18.00
cover GOOD NEWS! Your organization subscribes to the SPIE Digital Library. You may be able to download this paper for free. Check Access

Paper Abstract

This paper addresses an important question in machine learning: What kinds of network architectures work better on what kinds of problems? A projection pursuit learning network has a very similar structure to a one hidden layer sigmoidal neural network. A general method based on a continuous version of projection pursuit regression is developed to show that projection pursuit regression works better on angular smooth functions than on Laplacian smooth functions. There exists a ridge function approximation scheme to avoid the curse of dimensionality for approximating some class of underlying functions.

Paper Details

Date Published: 1 July 1992
PDF: 12 pages
Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140143
Show Author Affiliations
Ying Zhao, AI Lab./MIT (United States)
Christopher G. Atkeson, AI Lab./MIT (United States)

Published in SPIE Proceedings Vol. 1710:
Science of Artificial Neural Networks
Dennis W. Ruck, Editor(s)

© SPIE. Terms of Use
Back to Top