Title	Conservative architectures for deep neural networks
Creator	Haber, Eldad
Publisher	Banff International Research Station for Mathematical Innovation and Discovery
Date Issued	2019-06-26T10:46
Description	In this talk we discuss architectures for deep neural networks that preserve the energy of the propagated signal. We show that such networks can have significant computational advantages for some key problems in computer vision
Extent	36.0 minutes
Subject	Mathematics; Functional analysis; Calculus of variations and optimal control; optimization; Numerical analysis
Type	Moving Image
File Format	video/mp4
Language	eng
Notes	Author affiliation: The University of British Columbia
Series	BIRS Workshop Lecture Videos (Banff, Alta)
Date Available	2019-12-24
Provider	Vancouver : University of British Columbia Library
Rights	Attribution-NonCommercial-NoDerivatives 4.0 International
DOI	10.14288/1.0387311
URI	http://hdl.handle.net/2429/72948
Affiliation	Non UBC
Peer Review Status	Unreviewed
Scholarly Level	Faculty
Rights URI	http://creativecommons.org/licenses/by-nc-nd/4.0/
Aggregated Source Repository	DSpace

Open Collections

BIRS Workshop Lecture Videos