- Library Home /
- Search Collections /
- Open Collections /
- Browse Collections /
- BIRS Workshop Lecture Videos /
- Conservative architectures for deep neural networks
Open Collections
BIRS Workshop Lecture Videos
Featured Collection
BIRS Workshop Lecture Videos
Conservative architectures for deep neural networks Haber, Eldad
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
Item Metadata
Title |
Conservative architectures for deep neural networks
|
Creator | |
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 | |
Type | |
File Format |
video/mp4
|
Language |
eng
|
Notes |
Author affiliation: The University of British Columbia
|
Series | |
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 | |
Affiliation | |
Peer Review Status |
Unreviewed
|
Scholarly Level |
Faculty
|
Rights URI | |
Aggregated Source Repository |
DSpace
|
Item Media
Item Citations and Data
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International