Repeat Until Bored: A Pattern Selection Strategy

Part of Advances in Neural Information Processing Systems 4 (NIPS 1991)

Bibtex Metadata Paper

Authors

Paul Munro

Abstract

An alternative to the typical technique of selecting training examples independently from a fixed distribution is fonnulated and analyzed, in which the current example is presented repeatedly until the error for that item is reduced to some criterion value, ~; then, another item is ran(cid:173) domly selected. The convergence time can be dramatically increased or decreased by this heuristic, depending on the task, and is very sensitive to the value of ~.