2026-09-20T22:44:05Zhttps://api.drum.lib.umd.edu/server/oai/request

oai:drum.lib.umd.edu:1903/188382017-06-13T10:35:35Zcom_1903_2234com_1903_1654com_1903_2col_1903_2765col_1903_3

Chellappa, Rama Peng, Kang-Hao Digital Repository at the University of Maryland University of Maryland (College Park, Md.) Electrical Engineering 2016-09-15T05:35:08Z 2016-09-15T05:35:08Z 2016 https://doi.org/10.13016/M25V4B http://hdl.handle.net/1903/18838 (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 Mutual Information-based RBM Neural Networks Thesis Electrical engineering Computer science Deep Learning Mutual Information Neural Network Restricted Boltzmann Machine open.access