A maximum entropy interpretation of random access memory network computations

Citation

Luttrell S P, November 1990, A maximum entropy interpretation of random access memory network computations, RSRE technical report (Malvern, UK), SP4/137

Abstract

We briefly summarise the maximum entropy method and its application to the problem of assigning a probability measure in a state space. We show how one can impose constraints on the marginal probabilities to guarantee that the maximum entropy solution can be interpreted in terms of random access memory network (specifically WISARD) computations. We thus achieve a unification of the theoretical analyses of this type of network and Gibbs distribution (or Markov random field) networks.

Links

  • Remastered paper in Mathematica
  • Reproduction of results using Mathematica