Introduction

The energy function of the Hopfield network is determined by the exemplar patterns. The network weights are fixed by the patterns and there is no means of having the network learn the weights through exposure to them. The Boltzmann machine extends the capabilities of the Hopfield network by introducing an algorithm for the adaptive determination of the weights.

The Hopfield network finds local minima of the energy function. In many cases, this is sufficient, but in many cases, too, it is desirable to find the state which is the global minimum of the energy function. The Boltzmann machine combines the Hopfield network architecture with the process called simulated annealing in an effort to find a global minimum of the energy function.