Mutual Information-based RBM Neural Networks
dc.contributor.advisor | Chellappa, Rama | en_US |
dc.contributor.author | Peng, Kang-Hao | en_US |
dc.contributor.department | Electrical Engineering | en_US |
dc.contributor.publisher | Digital Repository at the University of Maryland | en_US |
dc.contributor.publisher | University of Maryland (College Park, Md.) | en_US |
dc.date.accessioned | 2016-09-15T05:35:08Z | |
dc.date.available | 2016-09-15T05:35:08Z | |
dc.date.issued | 2016 | en_US |
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. | en_US |
dc.identifier | https://doi.org/10.13016/M25V4B | |
dc.identifier.uri | http://hdl.handle.net/1903/18838 | |
dc.language.iso | en | en_US |
dc.subject.pqcontrolled | Electrical engineering | en_US |
dc.subject.pqcontrolled | Computer science | en_US |
dc.subject.pquncontrolled | Deep Learning | en_US |
dc.subject.pquncontrolled | Mutual Information | en_US |
dc.subject.pquncontrolled | Neural Network | en_US |
dc.subject.pquncontrolled | Restricted Boltzmann Machine | en_US |
dc.title | Mutual Information-based RBM Neural Networks | en_US |
dc.type | Thesis | en_US |
Files
Original bundle
1 - 1 of 1