Learning Gaussian-Bernoulli RBMs using Difference of Convex Functions Optimization

no code implementations • 11 Feb 2021 • Vidyadhar Upadhya, P S Sastry

It is seen that S-DCP is better than the CD and PCD algorithms in terms of speed of learning and the quality of the generative model learnt.

Efficient Learning of Restricted Boltzmann Machines Using Covariance Estimates

no code implementations • 25 Oct 2018 • Vidyadhar Upadhya, P. S. Sastry

Learning RBMs using standard algorithms such as CD(k) involves gradient descent on the negative log-likelihood.

Learning RBM with a DC programming Approach

no code implementations • 21 Sep 2017 • Vidyadhar Upadhya, P. S. Sastry

By exploiting the property that the RBM log-likelihood function is the difference of convex functions, we formulate a stochastic variant of the difference of convex functions (DC) programming to minimize the negative log-likelihood.

Empirical Analysis of Sampling Based Estimators for Evaluating RBMs

no code implementations • 8 Oct 2015 • Vidyadhar Upadhya, P. S. Sastry

The Restricted Boltzmann Machines (RBM) can be used either as classifiers or as generative models.