See this talk by Jeremy Howard: At Kaggle, It's a Disadvantage To Know Too Much and "Getting In Shape For The Sport Of Data Science" Start by practicing on toy datasets in MATLAB and walking through simple examples in Statistics and Neural Network Toolbox Below two books are standard introduction texts. They are complementary, the first one is written from a statistician perspective with lots of data analysis examples and the second one is focusing on algorithms. Both are graduate level texts requiring knowledge of algebra, statistics and calculus. It would also help to take a class on optimization but not strictly necessary. See this talk by Jeremy Howard: At Kaggle, It's a Disadvantage To Know Too Much and "Getting In Shape For The Sport Of Data Science" Below two books are standard introduction texts. They are complementary, the first one is written from a statistician perspective with lots of data analysis examples and the second one is focusing on algorithms.