Efficient Learning in Sparsely Connected Boltzmann Machines

We present a heuristical procedure for efficient estimation of the partition function in the Boltzmann distribution. The resulting speed-up is of immediate relevance for the speed-up of Boltzmann Machine learning rules, especially for networks with a sparse connectivity.

[1]  Michael I. Jordan,et al.  Learning in Boltzmann Trees , 1994, Neural Computation.

[2]  Geoffrey E. Hinton,et al.  A Learning Algorithm for Boltzmann Machines , 1985, Cogn. Sci..

[3]  David S. Johnson,et al.  Computers and Intractability: A Guide to the Theory of NP-Completeness , 1978 .

[4]  Hilbert J. Kappen,et al.  Learning Structure with Many-Take-All Networks , 1996, ICANN.

[5]  M. J. Nijman,et al.  Radial basis Boltzmann machines and learnng with missing values , 1995 .

[6]  Judea Pearl,et al.  Probabilistic reasoning using graphs , 1987, International Conference on Information Processing and Management of Uncertainty.