Artificial Intelligence: A Modern Approach

Computer science: Knuth's TAOCP. And Sipser's Introduction to the Theory of Computation. Programming: SICP, K&R, and Stroustrup. Siebel's Practical common lisp. Artificial intelligence: AI a modern approach. Signals and Systems: Oppenheim's book Probability and statistics: Probability Theory: The Logic of Science by Jaynes

At any given time I have somewhere around 50 books "in flight" in the sense that I've read at least a few pages and put it in "currently reading" status on Goodreads. But there's usually one (or two) that are getting the bulk of my attention. Right now the main book I'm focusing on is Artificial Intelligence: A Modern Approach by Norvig and Russell. I'd had this on my shelf for years and never got serious about working my way through the entire thing until recently. And I have to say, I now really regret not starting this project sooner. There's so much great stuff in this book. I'm not just "reading" it like a novel though. I "just read" up to a certain point (basically the end of the section on inference using FOL) and now I'm going back to a certain point (the beginning of the section on logic based agents) and going back through and doing exercises, implementing the algorithms myself, etc. Once I've satisfied myself that I have done all I need to do with this area, I'll pick back up with the section that starts talking about Uncertainty and repeat the process.…

I recommend reading http://aima.cs.berkeley.edu/ . Has great intro and goes into the details.

AI - A modern approach by Russell & Norvig. http://aima.cs.berkeley.edu/

Statistical learning is only one part of AI. If the person wants to learn about AI, wouldn't starting with something like "AI: A modern approach" he a better start?

AI: A Modern Approach (Russell, Norvig) and Deep Learning (Goodfellow, Bengio) have been mentioned already. I'd also recommend: Godel, Escher Bach: an Eternal Golden Braid by Douglas Hofstadter. Might not be exactly what you're looking for (it's all over the place, touching music theory, math, art, philosophy...), but it's fun and enjoyable to read. Also very dense.

You cannot really go practical in AI without academic rigor. You can do recipes of what's already been done using a TensorFlow book, but that's how far one can go. If one is serious in getting in AI today, a great way to do is read the following books, in order: 1. AI: A Modern Approach by Stuart Russell and Peter Norvig. 2. Deep Learning by Ian Goodfellow and Yoshua Bengio. It is amazing how approachable both books are for beginners, but you will be diving a lot into academic stuff as you go along.

Though it is an academic book, Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig. The first chapter in the book provides a detailed analysis of how other disciplines contribute to the idea of AI - from Philosophy to Psychology, Biology to Computer Science. Makes for an interesting read, even for a non-tech reader.

Artificial Intelligence: A Modern Approach is a great read!

edit: forget my answer. I didn't read them as ebooks for plain books: Windows Internals by Solomon and Russinovich AI: A modern Approach by Russell and Norvig

> "Artificial Intelligence: A Modern Approach" I think it is one of the best books written on any topic ever period. It is kinda advanced but also brilliant, and was a turning point in my decision to master hacking. > Now I am reading "Two Scoops of Django" and enjoying it A LOT. It's closer to a beginner/intermediate level, and it brings me a lot of joy and excitement about programming. > Another one is "Hackers & Painters", of course. PG is brilliant, nuff said. His book "ANSI Common Lisp" is definitely on the top of my reading list, I've already started and it is great. > Just to mention, a little less technical book is "Ghost In The Wires" by Kevin Mitnick, a famous hacker. I'm listening the audiobook now and it is really inspiring, entertaining and fantastic.

Artificial Intelligence, a Modern Approach (Russell & Norvig), while doing ai-class.com. Great writing for a text book. Coders at Work (Seibel).

Programming in Haskell by Graham Hutton A.I. A Modern Approach (ch 13-16) by Russell and Norvig A Tunnel In The Sky by Robert Heinlein The Revelation Space series (3 of the 5 books) by Alistair Reynolds Eon/Eternity (both by Greg Bear)

This is kind of moot, truthfully I'd go, now (or look first at, but they're both getting praise so...) for Chris Bishop or Ethem Alpaydin's new books. But between Norvig and Mitchell, Norvig has 138 pages on learning vs Mitchell's ~390, but, Mitchell's is from a different era, Norvig is easier to read - larger pages, more diagrams, better writing, and you know where you are better - and fresher material. To each his own. But like I say, I'd probably go with one of the even newer ones. For a while Mitchell was all there was, then Norvig came along, and now there're a few to choose from.

I've seen the Norvig book recommended by others on this site for ML, but I don't understand why: the Norvig book is an AI book, not an ML book. It only has a few chapters on learning, and IIRC much of that is on reinforcement learning. Obviously the Norvig book is very well-written and is good background for learning about ML, but I don't think it is a sufficient ML book as such. As far as ML goes, I found the "Programming Collective Intelligence" book to very readable and practical, but very light on the theoretical foundations (which is intentional, of course). I've got a copy of the Witten ML book ("Data Mining: Practical Machine Learning Tools and Techniques"), but to be honest I haven't gotten much from it yet, either: it doesn't seem to discuss SVMs in any detail, nor random forests or neural networks. But I haven't really dug into it yet.

I disagree wrt Mitchell; too dry and out-of-date. In its place I'd recommend the Norvig book which covers everything Mitchell does (IIRC) except 'Probably Approximately Correct' (PAC) learning. And, it's more up-to-date (Support Vector Machines) and is much more readable. Also, I haven't read it except a flip-through at a bookstore, but Christopher Bishop's one I'd look at (perhaps the Amazon comments).

Artificial Intelligence A Modern Approach SE, by Stuart Russell and Peter Norvig. I am a big fan of Peter Norvig in particular, he has a ton of great essays and code available online: http://norvig.com/