Article ID | Journal | Published Year | Pages | File Type |
---|---|---|---|---|
404332 | Neural Networks | 2012 | 5 Pages |
Abstract
We organized a challenge in “Unsupervised and Transfer Learning”: the UTL challenge (http://clopinet.com/ul). We made available large datasets from various application domains: handwriting recognition, image recognition, video processing, text processing, and ecology. The goal was to learn data representations that capture regularities of an input space for re-use across tasks. The representations were evaluated on supervised learning “target tasks” unknown to the participants. The first phase of the challenge was dedicated to “unsupervised transfer learning” (the competitors were given only unlabeled data). The second phase was dedicated to “cross-task transfer learning” (the competitors were provided with a limited amount of labeled data from “source tasks”, distinct from the “target tasks”). The analysis indicates that learned data representations yield significantly better results than those obtained with original data or data preprocessed with standard normalizations and functional transforms.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Isabelle Guyon, Gideon Dror, Vincent Lemaire, Daniel L. Silver, Graham Taylor, David W. Aha,