Unsupervised and Transfer Learning Challenge

PHASE 1: UNSUPERVISED LEARNING CHALLENGE

clopinet.com/ul

Do you believe that it is possible to LEARN from unlabeled data Representations of Similarity Measures that will then fare well in supervised learning tasks?

Now is your chance to prove it: you have 50 days to work on 5 unsupervised learning task from large real world databases.

Labeling data is not only expensive, it is tedious. When it comes to your own personal data it is also something you do not want to outsource. To help us tagging fast our personal pictures, videos, and documents, we need systems that can learn with very few training examples. The question is whether we can exploit similar data (labeled with different types of labels or completely unlabeled) to improve data preprocessing.

There will be publication opportunities at ICML, IJCNN, and in JMLR W&CP.