|
DSpace at MIT >
Computer Science and Artificial Intelligence Lab (CSAIL) >
CSAIL Digital Archive >
CSAIL Technical Reports (July 1, 2003 - present) >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1721.1/41517
|
| Title: | Transferring Nonlinear Representations using Gaussian Processes with a Shared Latent Space |
| Authors: | Urtasun, Raquel
Quattoni, Ariadna
Lawrence, Neil
Darrell, Trevor |
| Advisor: | Trevor Darrell |
| Other contributors: | Vision |
| Issue Date: | 11-Apr-2008 |
| Related To: | Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory
|
| 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. |
| URI: | http://hdl.handle.net/1721.1/41517 |
| Appears in Collections: | CSAIL Technical Reports (July 1, 2003 - present)
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| MIT-CSAIL-TR-2008-020.pdf | | 296Kb | Adobe PDF | View/Open | | MIT-CSAIL-TR-2008-020.ps | | 72Kb | PostScript | View/Open |
|
This item is protected by original copyright
|
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.
|
