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.*- Identifier
- https://doi.org/10.13016/M25V4B
- OAI identifier oai:identifier
- oai:drum.lib.umd.edu:1903/18838