An Adaptive Bayesian Pruning for Neural Networks in a Non-Stationary Environment

摘要

Pruning a neural network to a reasonable smaller size, and if possible to give a better generalization, ahs long been investigated. Conventionally the common technique of pruning is based on considering error sensi- tivty measure, and the nature of the problem being solved is usually stationary. In this article, we present an adaptive pruning algorithm for use in a nonstationary environment. The idea relies on the use of the extended Kalman filter (DKF) training method.