Global Optimisation of Neural Network Models via Sequential Sampling

Part of Advances in Neural Information Processing Systems 11 (NIPS 1998)

Authors

João de Freitas, Mahesan Niranjan, Arnaud Doucet, Andrew Gee

Abstract

We propose a novel strategy for training neural networks using se(cid:173) quential sampling-importance resampling algorithms. This global optimisation strategy allows us to learn the probability distribu(cid:173) tion of the network weights in a sequential framework. It is well suited to applications involving on-line, nonlinear, non-Gaussian or non-stationary signal processing.