- A first course in machine learning machine learning and pattern recognition
Really sort of similar to the previous book it covers virtually everything , you’re going to need to know as a beginner in machine learning , it covers classification, and clustering and we’ll talk about the algorithms that are used, and give you some of the derivations of those algorithms, and it’s done very well.
- The elements of statistical learning data mining inference and prediction
Now this is sort of the companion text to the previous book that I mentioned an introduction to statistical learning with applications in R, this is the sort of more advanced the chunkier version that goes more into the maths, and gives you more insight into how these algorithms work. I think it’s a great book and those two together , if you’re new you know read the other one first the is introduction to statistical learning and then this one and you’re pretty much covered .
- Artificial intelligence a modern approach by Stewart Russell
Now this book is really really well, known you know amongst students of AI and machine learning all around the world, it’s the recommended text in universities all over the world, and it’s a comprehensive book on all of the algorithms that are applied in artificial intelligence that of course machine learning too, and it teaches you the maths, you know it doesn’t assume you know all the maths behind these algorithms, and it teaches you that too
- Machine learning. probabilistic perspective by Kevin PbMurphy
Now this is more of a reference book, you know you probably wouldn’t buy a copy of this you can if you like, but you know you’re more likely to have access to it in a library, and you know really gain some insight into areas of machine learning that you’re not sure about .
- Pattern recognition and machine learning by Christopher Bishop
This is a really popular text in fact. I don’t know a machine learning lab that doesn’t have a copy of this it’s, often recommended for master students or people starting PhDs, it has a leaning towards Bayesian methods, but it’s very popular and covers most of what you will need in machine learning, it’s quite mathematical so don’t try to read it if you don’t have a mathematical background because it might put you off , but definitely again it’s not on one of those reference books that you should be.