Back to results

University of Maryland

Mutual Information-based RBM Neural Networks

Abstract

dc:description.abstract

(Deep) neural networks are increasingly being used for various computer vision and pattern recognition tasks due to their strong ability to learn highly discriminative features. However, quantitative analysis of their classication ability and design philosophies are still nebulous. In this work, we use information theory to analyze the concatenated restricted Boltzmann machines (RBMs) and propose a mutual information-based RBM neural networks (MI-RBM). We develop a novel pretraining algorithm to maximize the mutual information between RBMs. Extensive experimental results on various classication tasks show the eectiveness of the proposed approach.

Degree

thesis:*
Department dc:contributor.department
Electrical Engineering
Year dc:date.issued
2016

Author and committee

dc:creator, dc:contributor.*
Author dc:creator
  • Peng, Kang-Hao
Advisor dc:contributor.advisor
  • Chellappa, Rama

Rights

Language dc:language.iso
en

Identifiers

dc:identifier.*
OAI identifier oai:identifier
oai:drum.lib.umd.edu:1903/18838

Chain of custody

source
Harvested from
University of Maryland
Base URL
api.drum.lib.umd.edu/server/oai/request
Last updated
2026-07-24
Source record
OAI-PMH GetRecord
related terms
citation

Peng, Kang-Hao. Mutual Information-based RBM Neural Networks. 2016. http://hdl.handle.net/1903/18838