Show simple item record

dc.contributor.authorAghasi, Alireza
dc.date.accessioned2018-03-26T18:42:58Z
dc.date.available2018-03-26T18:42:58Z
dc.date.issued2018-03-14
dc.identifier.urihttp://hdl.handle.net/1853/59442
dc.descriptionPresented on March 14, 2018 at 12:00 p.m. in the Marcus Nanotechnology Building, Room 1116.en_US
dc.descriptionAlireza Aghasi is currently an assistant professor in the Institute for Insight at the Robinson College of Business at Georgia State University. His research fundamentally focuses on optimization theory and statistics, with applications to various areas of data science, artificial intelligence, modern signal processing and physics-based inverse problems.en_US
dc.descriptionRuntime: 58:09 minutesen_US
dc.description.abstractWe introduce and analyze a new technique for model reduction in deep neural networks. Our algorithm prunes (sparsifies) a trained network layer-wise, removing connections at each layer by addressing a convex problem. We present both parallel and cascade versions of the algorithm along with the mathematical analysis of the consistency between the initial network and the retrained model. We also discuss an ADMM implementation of Net-Trim, easily applicable to large scale problems. In terms of the sample complexity, we present a general result that holds for any layer within a network using rectified linear units as the activation. If a layer taking inputs of size N can be described using a maximum number of s non-zero weights per node, under some mild assumptions on the input covariance matrix, we show that these weights can be learned from O(slog N/s) samples.en_US
dc.format.extent58:09 minutes
dc.language.isoen_USen_US
dc.relation.ispartofseriesMachine Learning @ Georgia Tech (ML@GT) Seminaren_US
dc.subjectCompressed sensingen_US
dc.subjectDeep learningen_US
dc.subjectPruning neural networksen_US
dc.titlePruning Deep Neural Networks with Net-Trim: Deep Learning and Compressed Sensing Meeten_US
dc.typeLectureen_US
dc.typeVideoen_US
dc.contributor.corporatenameGeorgia Institute of Technology. Machine Learningen_US
dc.contributor.corporatenameGeorgia State University. J. Mack Robinson College of Businessen_US


Files in this item

This item appears in the following Collection(s)

Show simple item record