| dc.contributor.advisor |
Trevor Darrell |
en_US |
| dc.contributor.author |
Urtasun, Raquel |
en_US |
| dc.contributor.author |
Quattoni, Ariadna |
en_US |
| dc.contributor.author |
Lawrence, Neil |
en_US |
| dc.contributor.author |
Darrell, Trevor |
en_US |
| dc.contributor.other |
Vision |
en_US |
| dc.date.accessioned |
2008-05-05T15:46:05Z |
|
| dc.date.available |
2008-05-05T15:46:05Z |
|
| dc.date.issued |
2008-04-11 |
en_US |
| dc.identifier.other |
MIT-CSAIL-TR-2008-020 |
en_US |
| dc.identifier.uri |
http://hdl.handle.net/1721.1/41517 |
|
| dc.description.abstract |
When a series of problems are related, representations derived from learning earlier tasks may be useful in solving later problems. In this paper we propose a novel approach to transfer learning with low-dimensional, non-linear latent spaces. We show how such representations can be jointly learned across multiple tasks in a Gaussian Process framework. When transferred to new tasks with relatively few training examples, learning can be faster and/or more accurate. Experiments on digit recognition and newsgroup classification tasks show significantly improved performance when compared to baseline performance with a representation derived from a semi-supervised learning approach or with a discriminative approach that uses only the target data. |
en_US |
| dc.description.provenance |
Submitted by CSAIL Importer (publications-dspace@csail.mit.edu) on 2008-05-05T15:46:04Z
No. of bitstreams: 2
MIT-CSAIL-TR-2008-020.pdf: 303144 bytes, checksum: 82599a7c06366dfe5f91db1b810763d4 (MD5)
MIT-CSAIL-TR-2008-020.ps: 73870 bytes, checksum: 66f1b537d23576efd30b23b41f5ce8de (MD5) |
en |
| dc.description.provenance |
Made available in DSpace on 2008-05-05T15:46:05Z (GMT). No. of bitstreams: 2
MIT-CSAIL-TR-2008-020.pdf: 303144 bytes, checksum: 82599a7c06366dfe5f91db1b810763d4 (MD5)
MIT-CSAIL-TR-2008-020.ps: 73870 bytes, checksum: 66f1b537d23576efd30b23b41f5ce8de (MD5)
Previous issue date: 2008-04-11 |
en |
| dc.format.extent |
10 p. |
en_US |
| dc.relation |
Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory |
en_US |
| dc.relation |
|
en_US |
| dc.title |
Transferring Nonlinear Representations using Gaussian Processes with a Shared Latent Space |
en_US |
