Books

This book is focused on the practical side of machine learning. We did not present the thinking behind the algorithms or the theory that justify them. If you are interested in that aspect of machine learning, we recommend Pattern Recognition and Machine Learning, by Christopher Bishop. This is a classical introductory text in the field. It will teach you the nitty-gritty of most of the algorithms we used in this book.

If you want to move beyond the introduction and learn all the gory mathematical details, Machine Learning: A Probabilistic Perspective, by Kevin P. Murphy, is an excellent option (www.cs.ubc.ca/~murphyk/MLbook). It's very recent (published in 2012) and contains the cutting edge of ML research. This 1,100-page book can also serve as a reference, as very little of machine learning has been left out.

Specific to deep learning, you probably want to read Deep Learning, by Ian Goodfellow et al. (http://www.deeplearningbook.org). The book is more on the theoretical side, but still very accessible. Its web version is free of charge, but some books are just worth the investment. 

Blogs

Here is an obviously non-exhaustive list of blogs, which would be of interest for someone working in machine learning:

• Cross Validated: http://stats.stackexchange.com (OK, it is not really blog, but rather a question-and-answer site. The answers, though, are often so good that they could be published as blog posts as well.)
• Machine Learning Theory: http://hunch.net. The average pace is one post per month, very practical, always surprising approaches
• Edwin Chen's Blog: http://blog.echen.me. The average pace is one post per month, covering more applied topics
• Machined Learnings: http://www.machinedlearnings.com. The average pace is one post per month, covering more applied topics
• FlowingData: http://flowingdata.com. The average pace is one post per day, with the posts centering on statistics
• Simply Statistics: http://simplystatistics.org. Several posts per month, focusing on statistics and big data
• Statistical Modeling, Causal Inference, and Social Science: http://andrewgelman.com. One post per day, often often funny reads when the author points out flaws in popular media, using statistics

Data sources

If you want to play around with algorithms, you can obtain many datasets from the Machine Learning Repository at the University of California at Irvine (UCI). You can find it at http://archive.ics.uci.edu/ml.

Getting competitive

An excellent way to learn more about machine learning is by trying out a competition! Kaggle (http://www.kaggle.com) is a marketplace of ML competitions and was already mentioned in the introduction. On the website, you will find several different competitions with different structures, and often cash prizes.

The supervised learning competitions almost always follow this format: you (and every other competitor) are given access to labeled training data and testing data (without labels). Your task is to submit predictions for testing data. When the competition closes, whoever has the best accuracy wins. The prizes range from glory to cash.

Of course, winning something is nice, but you can gain a lot of useful experience just by participating. So, you have to stay tuned after the competition is over as participants start sharing their approaches in the forum. Most of the time, winning is not about developing a new algorithm, but cleverly preprocessing, normalizing, and combining existing methods.