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.
Keywords
- Hide Unit
- Generalization Error
- Multilayer Neural Network
- Niels Bohr Institute
- Committee Machine
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.