Recently I read an interesting article by Yaser S. Abu-Mostafa in the Scientific American about Machine Learning. Basically he is promoting the field of machine learning as a method to extract information from huge databases. He also mentions that he offers a free online course. Hence, I started the course two weeks ago. The course is still pretty basic only dealing with linear models. The next weeks should become more interesting as we dive into the theory. Hopefully, in a few weeks I can build my own machine learning tools (besides the linear programs).
During my time at the university I mostly worked with SAS. However, since then R has made a rapid development and I decided to learn R using the free e-book “An Introduction to Data Science” by Jeffrey Stanton. The power of R with all the available packages is amazing. Among others I learned how to extract tweets from Twitter with a given hashtag and make a wordcloud out of all these tweets. Examples below: