Here is the link: http://www.kaggle.com/c/SemiSupervisedFeatureLearning
50k samples with labels 1M samples without labels 1M features ~100 nonzero features per sample. The info has leaked that this is run by D. Sculley, the author of the minibatch k-means paper and the sofia-ml C++ library for scalable machine learning. The results of this challenge will be used in the related NIPS workshop. @pprett is currently #3 & I have made a poor test submission which is very bad and I am ashamed of :P I am pretty sure that the theano guys are gonna rock this :) -- Olivier http://twitter.com/ogrisel - http://github.com/ogrisel ------------------------------------------------------------------------------ All the data continuously generated in your IT infrastructure contains a definitive record of customers, application performance, security threats, fraudulent activity and more. Splunk takes this data and makes sense of it. Business sense. IT sense. Common sense. http://p.sf.net/sfu/splunk-d2dcopy1 _______________________________________________ Scikit-learn-general mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/scikit-learn-general
