Time Trials on Second-Order and Variable-Learning-Rate Algorithms

Part of Advances in Neural Information Processing Systems 3 (NIPS 1990)

Bibtex Metadata Paper

Authors

Richard Rohwer

Abstract

The performance of seven minimization algorithms are compared on five neural network problems. These include a variable-step-size algorithm, conjugate gradient, and several methods with explicit analytic or numerical approximations to the Hessian.