Brian Cheung, PhD Student, UC Berkeley - Deep Learning Summit 2015
This presentation took place at the Deep Learning Summit in San Francisco on 29-30 January 2015.
Supervised learning algorithms attempt to learn task relevant factors while being invariant to all others. In contrast, unsupervised learning algorithms seek latent factors which are relevant for a wide range of high level tasks. In this work, we combine these two ideas by augmenting autoencoders with a supervised learning cost to create a semi-super
3 views
0
0
1 month ago 00:02:45 1
Peggy Gou - (It Goes Like) Nanana - Official Video
1 month ago 00:04:01 1
Common, Pete Rock - Dreamin’
2 months ago 00:07:57 1
FKA twigs - Eusexua
3 months ago 00:02:55 1
Customers frustrated as fast-food prices continue to rise
4 months ago 00:02:51 1
Federal judge rules against Google in massive antitrust lawsuit