One thing my recent survey of freely available data sets did not uncover was a collection of archived RSS feeds. This surprised me a little since I would imagine aggregators like Bloglines, Google Reader and AideRSS must have large databases of hundreds of thousands of RSS feeds.
Having seen how easy it is to create an [...]
The upcoming Volume 9 of the Journal of Machine Learning Research is dedicated a chunk of its pages to a paper entitled “Evidence Contrary to the Statistical View of Boosting” by David Mease and Abraham Wyner. Following this is a number of responses by heavyweights including boosting’s earliest proponents, Freund and Schapire, as well as [...]