1 July 1992 How projection-pursuit learning works in high dimensions
Author Affiliations +
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.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Ying Zhao, Ying Zhao, Christopher G. Atkeson, Christopher G. Atkeson, } "How projection-pursuit learning works in high dimensions", Proc. SPIE 1710, Science of Artificial Neural Networks, (1 July 1992); doi: 10.1117/12.140143; https://doi.org/10.1117/12.140143
PROCEEDINGS
12 PAGES


SHARE
Back to Top