Multivariable Functional Interpolation and Adaptive Networks
D. S. Broomhead
Royal Signals and Radar Establishment,
St. Andrews Road, Great Malvern, Worcs. WR14 3PS, United Kingdom
David Lowe
Speech Research Unit, Royal Signals and Radar Establishment,
St. Andrews Road, Great Malvern, Worcs. WR14 3PS, United Kingdom
Abstract
The relationship between "learning" in adaptive layered networks and the fitting of data with high dimensional surfaces is discussed. This leads naturally to a picture of "generalization" in terms of interpolation between known data points and suggests a rational approach to the theory of such networks. A class of adaptive networks is identified which makes the interpolation scheme explicit. This class has the property that learning is equivalent to the solution of a set of linear equations. These networks thus represent nonlinear relationships while having a guaranteed learning rule.
