On-Line Learning in Multilayer Neural Networks
We present an analytic solution to the problem of on-line gradient-descent learning for two-layer neural networks with an arbitrary number of hidden units in both teacher and student networks. The technique, demonstrated here for the case of adaptive input-to-hidden weights, becomes exact as the dimensionality of the input space increases.
KeywordsHide Unit Generalization Error Multilayer Neural Network Niels Bohr Institute Committee Machine
Unable to display preview. Download preview PDF.