Pattern Recognition and Machine Learning

Gaussian Processes - with Pattern Recognition and Machine Learning by Christopher M. Bishop

1. The Goodfellow book is the obvious one. Another option is 'Machine Learning: A probabilistic perspective' by Kevin Murphy, which does have exercises but has less material on CNNs IIRC and is slightly older. Also Bishop 'Pattern Recognition and Machine Learning' is a classic reference but even older. 2. The Pedro Domingos book the Master Algorithm tries to address this itch / may be less philosophical that you want. It is >okay< but I don't think people love it.

Once you get your feet wet, the first year PHD course book for good theory is Pattern Recognition and Machine Learning by Bishop. But it could be a bit too theoretical - it provides a foundational mathematical framework and got me thinking about problems in a better way.

You don't need to focus on just one side or the other. AlphaGo wasn't made by just hacking together a couple neural nets, it built on heuristic search, MCTS, and the "old-school" AI. I agree that basic statistics + Bishop's book is a great way to start getting into machine learning -- but AI is a much broader field than that.

Firstly, I don't think you can dive straight into coding without understanding the fundamentals. AI is such a broad and rich field, and there's a lot you need to know before you start. It also depends on what you're going to focus on. Are you looking to implement a game-playing agent? An object recognition algorithm? More of a logic focus? If you just want Deep Learning and statistical methods, then Bishop's Pattern Recognition and Machine Learning is a good start. Otherwise, Russel and Norvig's Artificial Intelligence or Patrick Winston's similarly titled book are great starting points. For more big-picture stuff, Marvin Minsky's Society of Mind is great, and Hofstader's Gödel, Escher, Bach is a classic too. Both are a lot less practical though, which seems to be what you're looking for.

Some on this thread have recommended Norvig's PAIP, but that's kind of an old school AI book in that it focuses on heuristic search and logic (implementing prolog in lisp at one point, very impressive stuff actually); but is lacking any coverage of statistical machine learning, which is the approach that underlies most of the cool stuff these days. It's still a great book, but I'd instead recommend a path that focuses on machine learning: - The Master Algorithm: made for a general audience, gives you a lay of the land - Python Machine Learning by Sebastian Raschka: gives you practical skills using python, scikit-learn, numpy, jupyter notebooks, pandas etc. From zero to kaggle in 4 chapters, goes deeper after that. Also goes into enough theory you aren't flying completely blind.…

I would buy and look into the following books: # HTTP: The Definitive Guide - O'Reilly Media # Algorithms by Sedgewick # Introduction to Algorithms by Cormen. Check out some Machine Learning books: # Pattern Recognition and Machine Learning # Computer Networks (5th Edition) I would look at the following book if you wanted more Q&A and interview questions: # Cracking the Coding Interview: 150 Programming Questions ... Tutorial memberships: # I would buy a Tuts+ account, they have been very slow in releasing new content (too bad), however they have lots of great Web Development stuff. I would read some other non-technical books: # Hackers & Painters: Big Ideas from the Computer Age by Paul Graham # The Hard Thing About Hard Things by Ben Horowitz # The Innovator's Dilemma: The Revolutionary Book That Will Change The Way You Do Business by Clayton M. Christenen, # Thinking, Fast and Slow by Daniel Kahneman # How to Win Friends and Influence People by Dale Carnegie If you wanted to understand some Cloud stuff, look into the Whitepapers from Amazon Web Services: # https://aws.amazon.com/whitepapers/

let me know if you guys find better replacements, but this is what I got on my list: O'Reilly - Scott Murray - Interactive Data Visualization for the Web Data Visualization with D3.js Cookbook A First Course in Probability Rails AntiPatterns - Best Practice Ruby on Rails Refactoring Bayesian Data Analysis Andrew Gelma The Pragmatic Programmer Code Complete Bishop - Pattern Recognition and Machine Learning O'Reilly Mining The Social Web

Buddhism: Not Always So, and anything else by Shunryu Suzuki, What Buddha Taught, by Rahula Smarter: A Mathematical Bridge by Stephen Hewson, it will make you grok the real structure of mathematics even if you're starting with fairly basic undergraduate level math, and it will make it immensely easier to tackle new areas of mathematics. Pattern recognition and machine learning by Bishop Popular: Coders at Work, Founders at Work, Behind the Cloud

Also Bishop is much harder to read, so for a first introduction I think that Mitchell is good. There are some chapters on theoretical learning that you can skip, but I do think that it is good for a first overview of the field. This is the first time I hear about Marsland's book, so I can't comment on that.

The Mitchell book is definitely showing its age these days. It's not terrible, but anyone thinking of buying it should be aware that it is a broad but shallow tour of machine learning as it stood 15 years ago, and machine learning as a field has changed significantly since then. Most notably, there has been something of a Bayesian revolution that Mitchell basically ignores (understandable since the book predates it). Don't take this as a recommendation, because I haven't read it, but Stephen Marsland's Machine Learning book appears from a glance at the table of contents to be a much more modern attempt to provide the same type of coverage as Mitchell. But again, I can't speak to its quality. Chris Bishop's Pattern Recognition book is also very good, but it's not the same sort of book. Bishop is exhaustively deep on the narrower range of ML that he covers, but you won't get the same sort of coverage of the wider view of the field.

I didn't particularly like the WEKA book, but Bishop's book is excellent. If you're interested in introductory data mining stuff, I would recommend Tan's Introduction to Data Mining: http://www-users.cs.umn.edu/~kumar/dmbook/index.php

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).

If you want a fairly easy read without too many equations, try: Data Mining: Practical Machine Learning Tools and Techniques (Second Edition) http://www.cs.waikato.ac.nz/~ml/weka/book.html Which goes nicely with the Weka open source ML toolkit http://www.cs.waikato.ac.nz/ml/weka/ (although it is a good read without the toolkit) If you want a bit more math, I really like the recent (Oct 2007) book: Pattern Recognition and Machine Learning by Christopher M. Bishop http://www.amazon.com/Pattern-Recognition-Learning-Informati... (http://www.amazon.com/Pattern-Recognition-Learning-Information-Statistics/dp/0387310738) It is nicely self contained, going through all the stats you'll need.