search for: icml07

...ule. *Using unlabeled data:* Over the last 3-4 years a lot of papers have identified the importance of using unlabeled data to assist the task at hand by using it during feature extraction stage. Andrew Ng proposed a Self-Taught learning framework[ICML'07 paper<http://ai.stanford.edu/~hllee/icml07-selftaughtlearning.pdf>] wherein they make use of unlabeled data to improve performance. A very recent paper at ICML'11<http://eprints.pascal-network.org/archive/00008597/01/342_icmlpaper.pdf>used the advantage of feature learning using unlabeled data and beat the state-of-the-art in s...