Thursday, November 06, 2014
So, Google is scanning all the books ever published and is making good progress. An interesting project span off from all text scanned is the Google books NGram viewer project that curated all the words/phrases' traces in the publishing history. The raw data is also available for anyone interested in playing with a big set of interesting data. Here is my take on "Statistical learning" vs. "Statistical modeling" vs "predictive analytics".