Learning is essential to most of these neural network architectures and hence the choice of a learning algorithm is a central issue in network development. What is really meant by saying that a processing element learns? Learning implies that a processing unit is capable of changing its input/output behavior as a result of changes in the environment. Since the activation rule is usually fixed when the network is constructed and since the input/output vector cannot be changed, to change the input/output behavior the weights corresponding to that input vector need to be adjusted. A method is thus needed by which, at least during a training stage, weights can be modified in response to the input/output process. A number of such learning rules are available for neural network models. In a neural network, learning can be supervised, in which the network is provided with the correct answer for the output during training, or unsupervised, in which no external teacher is present.
Copyright 1996 by Ingrid Russell.