Sample Sizes for Threshold Networks with Equivalences
Information and Computation, 118, (1), .
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 site for reliable learning can be bounded above by a formula similar to that required for single output networks with no equivalences. The best previously obtained bounds are improved for all cases.
Actions (login required)