Some Approximation Properties of Projection Pursuit Learning Networks

Part of Advances in Neural Information Processing Systems 4 (NIPS 1991)

Bibtex Metadata Paper

Authors

Ying Zhao, Christopher Atkeson

Abstract

This paper will address an important question in machine learning: What kind of network architectures work better on what kind 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 func(cid:173) tions than on Laplacian smooth functions. There exists a ridge function approximation scheme to avoid the curse of dimensionality for approxi(cid:173) mating functions in L2(¢d).