Algebraic geometrical methods for hierarchical learning machines

Abstract

Hierarchical learning machines such as layered perceptrons, radial basis functions, Gaussian mixtures are non-identifiable learning machines, whose Fisher information matrices are not positive definite. This fact shows that conventional statistical asymptotic theory cannot be applied to neural network learning theory, for example either the Bayesian a posteriori probability distribution does not converge to the Gaussian distribution, or the generalization error is not in proportion to the number of parameters. The purpose of this paper is to overcome this problem and to clarify the relation between the learning curve of a hierarchical learning machine and the algebraic geometrical structure of the parameter space. We establish an algorithm to calculate the Bayesian stochastic complexity based on blowing-up technology in algebraic geometry and prove that the Bayesian generalization error of a hierarchical learning machine is smaller than that of a regular statistical model, even if the true distribution is not contained in the parametric model.