Sign inSign up
Identifiability of Priors from Bounded Sample Sizes with Applications to Transfer Learning thumbnail
slide-image
Pause
Mute
Subtitles not available
Playback speed
0.25
0.5
0.75
1
1.25
1.5
1.75
2
Full screen

Identifiability of Priors from Bounded Sample Sizes with Applications to Transfer Learning

Published on Aug 02, 20113380 Views

Steve Hanneke

We explore a transfer learning setting, in which a finite sequence of target concepts are sampled independently with an unknown distribution from a known family. We study the total number of labeled

COLT 2011 - Budapest

Related categories

Transfer Learning

Chapter list

Identifiability of Priors from Bounded Sample Sizes with Applications to Transfer Learning00:00
Outline00:51
Formal Model01:26
Identifiability of Priors from Joint Distributions - 102:46
Identifiability of Priors from Joint Distributions - 203:44
Identifiability of Priors from Joint Distributions - 407:30
Identifiability of Priors from Joint Distributions - 509:37
Identifiability of Priors from Joint Distributions - 612:08
Identifiability of Priors from Joint Distributions - 713:14
Identifiability of Priors from Joint Distributions - 814:49
Transfer Learning15:03
Statistical Information - 116:03
Statistical Information - 216:30
Formal Model16:57
Estimating the prior18:19
Transfer Learning20:02
Is this Better than without Transfer?21:31
Interesting Notes22:16
The End22:18