Training a Restricted Boltzmann Machine Using Spatial Markov Random Field Priors on Weights

Update item information
Publication Type thesis
School or College College of Engineering
Department School of Computing
Author Singhal, Shweta
Title Training a Restricted Boltzmann Machine Using Spatial Markov Random Field Priors on Weights
Date 2017
Description Recent developments have shown that restricted Boltzmann machines (RBMs) are useful in learning the features of a given dataset in an unsupervised manner. In the case of digital images, RBMs consider the image pixels as a set of real-valued random variables, disregarding their spatial layout. However, as we know, each image pixel is correlated with its neighboring pixels, and direct modeling of this correlation might help in learning. Therefore, this thesis proposes using a Markov random field prior on the weights of the RBM model, which is designed to model these correlations between neighboring pixels. We compared the test classification error of our model with that of a traditional RBM with no prior on the weights and with RBMs with L1 and L2 regularization prior on the weights. We used the NIST dataset, which consists of images of handwritten digits for our experiments.
Type Text
Publisher University of Utah
Subject Computer science
Dissertation Name Master of Science
Language eng
Rights Management (c) Shweta Singhal
Format Medium application/pdf
ARK ark:/87278/s67q3r1m
Setname ir_etd
Date Created 2019-10-18
Date Modified 2019-10-21
ID 1469491
Reference URL https://collections.lib.utah.edu/ark:/87278/s67q3r1m
Back to Search Results