Ridge polynomial networks
Authors:
- J. GhoshJGJ. Ghosh
- 1 May 1995
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Networks
- Vol. 6 (3) , 610-622
Abstract
This paper presents a polynomial connectionist network called ridge polynomial network (RPN) that can uniformly approximate any continuous function on a compact set in multidimensional input space R/sup d/, with arbitrary degree of accuracy. This network provides a more efficient and regular architecture compared to ordinary higher-order feedforward networks while maintaining their fast learning property. The ridge polynomial network is a generalization of the pi-sigma network and uses a special form of ridge polynomials. It is shown that any multivariate polynomial can be represented in this form, and realized by an RPN. Approximation capability of the RPN's is shown by this representation theorem and the Weierstrass polynomial approximation theorem. The RPN provides a natural mechanism for incremental network growth. Simulation results on a surface fitting problem, the classification of high-dimensional data and the realization of a multivariate polynomial function are given to highlight the capability of the network. In particular, a constructive learning algorithm developed for the network is shown to yield smooth generalization and steady learning.Keywords
This publication has 21 references indexed in Scilit:
- Neural Networks and the Bias/Variance DilemmaNeural Computation, 1992
- Universal Approximation Using Radial-Basis-Function NetworksNeural Computation, 1991
- A tree-structured adaptive network for function approximation in high-dimensional spacesIEEE Transactions on Neural Networks, 1991
- Self-organizing network for optimum supervised learningIEEE Transactions on Neural Networks, 1990
- The Stone-Weierstrass theorem and its application to neural networksIEEE Transactions on Neural Networks, 1990
- Higher order associative memories and their optical implementationsNeural Networks, 1988
- Learning, invariance, and generalization in high-order neural networksApplied Optics, 1987
- Projection PursuitThe Annals of Statistics, 1985
- Projection Pursuit Density EstimationJournal of the American Statistical Association, 1984
- Projection Pursuit RegressionJournal of the American Statistical Association, 1981