Title:
Few-shot Learning with Meta-Learning: Progress Made and Challenges Ahead
Few-shot Learning with Meta-Learning: Progress Made and Challenges Ahead
dc.contributor.author | Larochelle, Hugo | |
dc.contributor.corporatename | Georgia Institute of Technology. Machine Learning | en_US |
dc.contributor.corporatename | Google Brain | en_US |
dc.date.accessioned | 2018-10-30T21:15:33Z | |
dc.date.available | 2018-10-30T21:15:33Z | |
dc.date.issued | 2018-10-15 | |
dc.description | Presented on October 15, 2018 at 12:15 pm in the Marcus Nanotechnology Building, Rooms 1116. | en_US |
dc.description | Hugo Larochelle is a Research Scientist at Google Brain and lead of the Montreal Google Brain team. Larochelle also co-founded Whetlab, which was acquired in 2015 by Twitter, where he then worked as a Research Scientist in the Twitter Cortex group. | en_US |
dc.description | Runtime: 63:15 minutes | en_US |
dc.description.abstract | A lot of the recent progress on many AI tasks enabled in part by the availability of large quantities of labeled data. Yet, humans are able to learn concepts from as little as a handful of examples. Meta-learning is a very promising framework for addressing the problem of generalizing from small amounts of data, known as few-shot learning. In meta-learning, our model is itself a learning algorithm: it takes input as a training set and outputs a classifier. For few-shot learning, it is (meta-)trained directly to produce classifiers with good generalization performance for problems with very little labeled data. In this talk, I'll present an overview of the recent research that has made exciting progress on this topic (including my own) and will discuss the challenges as well as research opportunities that remain. | en_US |
dc.format.extent | 63:15 minutes | |
dc.identifier.uri | http://hdl.handle.net/1853/60506 | |
dc.language.iso | en_US | en_US |
dc.relation.ispartofseries | Machine Learning @ Georgia Tech (ML@GT) Seminar Series | |
dc.subject | Deep learning | en_US |
dc.subject | Few-shot learning | en_US |
dc.subject | Meta-learning | en_US |
dc.title | Few-shot Learning with Meta-Learning: Progress Made and Challenges Ahead | en_US |
dc.type | Moving Image | |
dc.type.genre | Lecture | |
dspace.entity.type | Publication | |
local.contributor.corporatename | Machine Learning Center | |
local.contributor.corporatename | College of Computing | |
local.relation.ispartofseries | ML@GT Seminar Series | |
relation.isOrgUnitOfPublication | 46450b94-7ae8-4849-a910-5ae38611c691 | |
relation.isOrgUnitOfPublication | c8892b3c-8db6-4b7b-a33a-1b67f7db2021 | |
relation.isSeriesOfPublication | 9fb2e77c-08ff-46d7-b903-747cf7406244 |
Files
Original bundle
1 - 4 of 4
No Thumbnail Available
- Name:
- larochelle.mp4
- Size:
- 621.52 MB
- Format:
- MP4 Video file
- Description:
- Download video
No Thumbnail Available
- Name:
- larochelle_videostream.html
- Size:
- 1.01 KB
- Format:
- Hypertext Markup Language
- Description:
- Streaming video
No Thumbnail Available
- Name:
- transcription.txt
- Size:
- 59.37 KB
- Format:
- Plain Text
- Description:
- Transcription
- Name:
- thumbnail.jpg
- Size:
- 45.15 KB
- Format:
- Joint Photographic Experts Group/JPEG File Interchange Format (JFIF)
- Description:
- Thumbnail
License bundle
1 - 1 of 1
No Thumbnail Available
- Name:
- license.txt
- Size:
- 3.13 KB
- Format:
- Item-specific license agreed upon to submission
- Description: