Location: Zoom https://harvard.zoom.us/j/779283357?pwd=MitXVm1pYUlJVzZqT3lwV2pCT1ZUQT09
Time: Tuesday, May 18, 2021, 10:00 AM (Eastern US), 15:00 (UK/Eire), 16:00 (Central Europe), 22:00 (China)
Title: The Energy-Based Learning Model
Abstract: One of the hottest sub-topics of machine learning in recent times has been Self-Supervised Learning (SSL). In SSL, a learning machine captures the dependencies between input variables, some of which may be observed, denoted X, and others not always observed, denoted Y. SSL pre-training has revolutionized natural language processing and is making very fast progress in speech and image recognition. SSL may enable machines to learn predictive models of the world through observation, and to learn representations of the perceptual world, thereby reducing the number of labeled samples or rewarded trials to learn a downstream task. In the Energy-Based Model framework (EBM), both X and Y are inputs, and the model outputs a scalar energy that measures the degree of incompatibility between X and Y. EBMs are implicit functions that can represent complex and multimodal dependencies between X and Y. EBM architectures belong to two main families: joint embedding architectures and latent-variable generative architectures. There are two main families of methods to train EBMs: contrastive methods, and volume regularization methods. Much of the underlying mathematics of EBM is borrowed from statistical physics, including concepts of partition function, free energy, and variational approximations thereof.
Additional Ways to Join
Join by telephone (use any number to dial in)
+1 929 436 2866
+1 312 626 6799
+1 669 900 6833
400 669 9381 China Toll-free
International numbers available: https://harvard.zoom.us/u/aclg6kOggb
One tap mobile: +19294362866,,779283357# US (New York)
Join by SIP conference room system
Meeting ID: 779 283 357
779283357@zoomcrc.com
Attachments
LOCATION:Zoom STATUS:CONFIRMED DTSTART:20210518T140000Z DTEND:20210518T140000Z END:VEVENT END:VCALENDAR