Ask HN: Best book on machine learning?
I am wondering what the HN community will recommend as the best book on machine learning, specially for computer vision with Caffe or TensorFlow.
If you haven't done significant mathematical stuff by yourself (like, do all the problems in a math book by yourself without anyone else telling you what to do), go get a degree. MS in CS is probably best, those are surprisingly easy to get into.
Otherwise, Haykin's Neural Networks and Learning Machines is best in my opinion (http://www.amazon.com/Neural-Networks-Learning-Machines-3rd/...). Bengio's Deep Learning book is the most current by far (http://www.deeplearningbook.org/). Otherwise, you read papers.
Note that all of these will deal nearly exclusively with the mathematics. Otherwise, you are following tutorials and wouldn't need any actual knowledge to do things. Some of the mathematics is a year old: some of the mathematics is 50 years old, some of it has been around since Gauss.
If by "college algebra" you mean that you learned basic algebra (fundamental theorem, equation solving, memorize solution to quadratic equation) in college, you need to learn calculus in one and then many dimensions (most of the people I know who are doing research-level things in machine learning learned this stuff in 6th to 8th grade, but who cares, especially if you are merely doing applications). Then, you learn linear algebra.