Luttrell S P, 1995, Designing analysable networks, in Handbook of Neural Computation (, IOP and OUP, ed. Fiesler E and Beale R), pp. B5.3:1-B5.3:8
In this section a unified theoretical model of unsupervised neural networks based on the theoretical ideas in (Luttrell) is presented. The analysis starts with a probabilistic model of the discrete neuron firing events that occur when a set of neurons is exposed to an input vector, and then uses Bayes' theorem to build a probabilistic description of the input vector from knowledge of the firing events. This sets the scene for unsupervised training of the network, by minimisation of the expected value of a distortion measure between the true input vector and the input vector inferred from the firing events. Various models of this type are investigated. For instance, if the model of the neurons permits firing to occur only within a defined cluster of neurons, and further, that only one firing event is observed, then the theory approximates the well-known topographic mapping network (Kohonen).