Consistency of Pseudolikelihood Estimation of Fully Visible Boltzmann Machines
- 1 October 2006
- journal article
- Published by MIT Press in Neural Computation
- Vol. 18 (10) , 2283-2292
Abstract
A Boltzmann machine is a classic model of neural computation, and a number of methods have been proposed for its estimation. Most methods are plagued by either very slow convergence or asymptotic bias in the resulting estimates. Here we consider estimation in the basic case of fully visible Boltzmann machines. We show that the old principle of pseudolikelihood estimation provides an estimator that is computationally very simple yet statistically consistent.Keywords
This publication has 6 references indexed in Scilit:
- Training Products of Experts by Minimizing Contrastive DivergenceNeural Computation, 2002
- Efficient Learning in Boltzmann Machines Using Linear Response TheoryNeural Computation, 1998
- Consistency of the Maximum Pseudo-Likelihood Estimator of Continuous State Space Gibbsian ProcessesThe Annals of Applied Probability, 1995
- A learning algorithm for boltzmann machinesCognitive Science, 1985
- A Learning Algorithm for Boltzmann Machines*Cognitive Science, 1985
- Statistical Analysis of Non-Lattice DataJournal of the Royal Statistical Society: Series D (The Statistician), 1975