Luttrell S P, March 1990, Error measures in adaptive networks, RSRE technical report (Malvern, UK), SP4/111
The main purpose of this note is to remove the need to assume that the output of a network has to be trained using an arbitrary choice of error measure, such as L2. The solution to this problem is subtle and indirect, and it requires one to embed the network model in a Bayesian framework. Thus we develop a Bayesian framework for constructing data generation models which may be inverted to yield the posterior probability over classes, and show how maximising relative entropy (of posterior probabilities) leads to adaptive networks that are similar (or identical) to standard network models (such as the multilayer perceptron network, radial basis function network, and hidden Markov model network)