If you already have a little exposure to machine learing, let me recomend an interesting review paper [1] on random forests: <a href="http://research.microsoft.com/pubs/155552/decisionForests_MSR_TR_2011_114.pdf" rel="nofollow">http://research.microsoft.com/pubs/155552/decisionForests_MS...</a><p>It isn't everything you need know in 30 minutes, but it's a concrete coverage of lots of topics in machine learning in under 150 pages. Here's why I'm recomending this paper:<p>* The algoritm is easy to understand.<p>* It can handle classification, regression, semi-supervised learning, manifold learning, and density estimation. The paper gives an introduction to each of these topics as well as a unified framework to implement each algorithm.<p>* It can handle categorical data and missing data [2]<p>* It gives as good results as other state of the art algorithms.<p>* The paper is well-written and easy to understand for someone without a deep background in machine learning.<p>[1] It's mostly a review paper. Using random forests for density estimation is new.<p>[2] This review paper doesn't cover categorical data or missing data.
Hilary Mason has a longer introduction to machine learning video using web data, however, it isn't free.<p><a href="http://shop.oreilly.com/product/0636920017493.do" rel="nofollow">http://shop.oreilly.com/product/0636920017493.do</a>
Nice talk. The example of google translate is not a good one though. Say you translate from language A to language B with 99% accuracy, and vice versa, which would be pretty awesome, you'd still have a substantial quality decay after only a few back and forth translations (0.99^x where x is the number of translation steps).
For more advanced audiences, here's a great resource I discovered recently: <a href="http://videolectures.net/mlss09uk_cambridge/" rel="nofollow">http://videolectures.net/mlss09uk_cambridge/</a> -- 60 hours of lectures from the giants of machine learning delivered at a summer school held at Cambridge in 2009.