A Probabilistic Framework for Deep Learning

Simple item page
dc.citation.journalTitleAdvances in Neural Information Processing Systems 29en_US
dc.contributor.authorPatel, Ankit B.en_US
dc.contributor.authorNguyen, Tanen_US
dc.contributor.authorBaraniuk, Richard G.en_US
dc.date.accessioned2017-01-09T18:24:39Zen_US
dc.date.available2017-01-09T18:24:39Zen_US
dc.date.issued2016en_US
dc.descriptionNEWS COVERAGE: A news release based on this journal publication is available online: http://news.rice.edu/2016/12/16/rice-baylor-team-sets-new-mark-for-deep-learning/en_US
dc.description.abstractWe develop a probabilistic framework for deep learning based on the Deep Rendering Mixture Model (DRMM), a new generative probabilistic model that explicitly capture variations in data due to latent task nuisance variables. We demonstrate that max-sum inference in the DRMM yields an algorithm that exactly reproduces the operations in deep convolutional neural networks (DCNs), providing a first principles derivation. Our framework provides new insights into the successes and shortcomings of DCNs as well as a principled route to their improvement. DRMM training via the Expectation-Maximization (EM) algorithm is a powerful alternative to DCN back-propagation, and initial training results are promising. Classification based on the DRMM and other variants outperforms DCNs in supervised digit classification, training 2-3x faster while achieving similar accuracy. Moreover, the DRMM is applicable to semi-supervised and unsupervised learning tasks, achieving results that are state-of-the-art in several categories on the MNIST benchmark and comparable to state of the art on the CIFAR10 benchmark.en_US
dc.identifier.citationPatel, Ankit B., Nguyen, Tan and Baraniuk, Richard G.. "A Probabilistic Framework for Deep Learning." <i>Advances in Neural Information Processing Systems 29,</i> (2016) Neural Information Processing Systems Foundation, Inc.: <a href="https://hdl.handle.net/1911/93745">https://hdl.handle.net/1911/93745</a>.en_US
dc.identifier.urihttps://hdl.handle.net/1911/93745en_US
dc.language.isoengen_US
dc.publisherNeural Information Processing Systems Foundation, Inc.en_US
dc.relation.urihttp://papers.nips.cc/paper/6231-a-probabilistic-framework-for-deep-learningen_US
dc.titleA Probabilistic Framework for Deep Learningen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpublisher versionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
ToDL-NIPS2016.pdf
Size:
2.85 MB
Format:
Adobe Portable Document Format
Description:
Download
Collections
Faculty Publications
ECE Publications