Transfering Nonlinear Representations using Gaussian Processes with a Shared Latent Space
When a series of problems are related, representations derived fromlearning earlier tasks may be useful in solving later problems. Inthis paper we propose a novel approach to transfer learning withlow-dimensional, non-linear latent spaces. We show how suchrepresentations can be jointly learned acros...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Published: |
2007
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/1721.1/39426 |
| Summary: | When a series of problems are related, representations derived fromlearning earlier tasks may be useful in solving later problems. Inthis paper we propose a novel approach to transfer learning withlow-dimensional, non-linear latent spaces. We show how suchrepresentations can be jointly learned across multiple tasks in adiscriminative probabilistic regression framework. When transferred tonew tasks with relatively few training examples, learning can befaster and/or more accurate. Experiments on a digit recognition taskshow significantly improved performance when compared to baselineperformance with the original feature representation or with arepresentation derived from a semi-supervised learning approach. |
|---|