A Comparison of Nonlinear Optimisation Strategies for Feed-Forward Adaptive Layered Networks
Andrew R. Webb, David G. Lowe, M.D. Bedworth · 1988
Abstract : This work discusses various learning strategies which may be employed for the generic class of layered feed-forward adaptive networks exemplified by the traditional Multilayer Perceptron. Such a network is only useful if a set of weight values exists which allows the network to form a good approximation to an underlying (and possibly unknown) transformation between input and output patterns.