ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Empirical Analysis of Sampling Based Estimators for Evaluating RBMs

Upadhya, Vidyadhar and Sastry, PS (2016) Empirical Analysis of Sampling Based Estimators for Evaluating RBMs. In: 22nd International Conference on Neural Information Processing (ICONIP), NOV 09-12, 2015, Istanbul, TURKEY, pp. 545-553.

Full text not available from this repository. (Request a copy)
Official URL: http://dx.doi.org/10.1007/978-3-319-26535-3_62


The Restricted Boltzmann Machines (RBM) can be used either as classifiers or as generative models. The quality of the generative RBM is measured through the average log-likelihood on test data. Due to the high computational complexity of evaluating the partition function, exact calculation of test log-likelihood is very difficult. In recent years some estimation methods are suggested for approximate computation of test log-likelihood. In this paper we present an empirical comparison of the main estimation methods, namely, the AIS algorithm for estimating the partition function, the CSL method for directly estimating the log-likelihood, and the RAISE algorithm that combines these two ideas.

Item Type: Conference Proceedings
Series.: Lecture Notes in Computer Science
Additional Information: Copy right for this article belongs to the SPRINGER INT PUBLISHING AG, GEWERBESTRASSE 11, CHAM, CH-6330, SWITZERLAND
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 06 Apr 2016 06:51
Last Modified: 06 Apr 2016 06:51
URI: http://eprints.iisc.ac.in/id/eprint/53641

Actions (login required)

View Item View Item