Part of Advances in Neural Information Processing Systems 4 (NIPS 1991)
John Shawe-Taylor
This paper applies the theory of Probably Approximately Correct (PAC) learning to multiple output feedforward threshold networks in which the weights conform to certain equivalences. It is shown that the sample size for reliable learning can be bounded above by a formula similar to that required for single output networks with no equivalences. The best previ(cid:173) ously obtained bounds are improved for all cases.