An approach to guaranteeing generalisation in neural networks.

Abstract

A novel approach to generalisation is presented that is able, under certain circumstances, to guarantee the generalisation to binary-output data for which no targets have been given. The basis of the guarantee is the recognition of a persistent global minimum error solution. An empirical test for whether the guarantee holds is provided which uses a technique called target reversal. The technique employs two neural networks whose convergence using opposing targets signals validity of the guarantee.