Part of Neural Information Processing Systems 0 (NIPS 1987)
Information retrieval in a neural network is viewed as a procedure in
which the network computes a "most probable" or MAP estimate of the unk(cid:173) nown information. This viewpoint allows the class of probability distributions, P, the neural network can acquire to be explicitly specified. Learning algorithms for the neural network which search for the "most probable" member of P can then be designed. Statistical tests which decide if the "true" or environmental probability distribution is in P can also be developed. Example applications of the theory to the highly nonlinear back-propagation learning algorithm, and the networks of Hopfield and Anderson are discussed.