Ask HN: Best books on AI? • Hacker News Board

Re: Ask HN: Best books on AI?

#91

Post by jaddood » Sun, Mar 19, 2017, 7:57 PM UTC

nabla9 wrote: post #63

nextos wrote: post #35

Earlier quoted context omitted.

I love Paradigms of Artificial Intelligence by Peter Norvig much more than AIMA, which I found excessively encyclopedic and shallow. While some will argue it is dated, I think it presents many timeless ideas that will get in vogue soon with little tweaks to their inference schemes. Same for The Art of Prolog.

It's Paradigms of Artificial Intelligence Programming (PAIP) http://norvig.com/paip.html AIMA provides better introduction for wider area of subjects but PAIP is one of most elegant and timeless books for both programming and old school AI.

Why not both?

Re: Ask HN: Best books on AI?

#92

Post by mavmak » Sun, Mar 19, 2017, 8:38 PM UTC

giardini wrote: post #83

Sometimes its best to answer a question with a question. Are you simply curious or is there something more pressing? For example, do you want some light reading or have you perhaps been asked to implement machine learning for your company? Most answers here assume you want to jump into the ML swamp and start analyzing your trove of "big data" ASAP. But is that so?

I want to have a basic understanding on the topic, and implement something small, maybe a side project.

Re: Ask HN: Best books on AI?

#93

Post by fapjacks » Mon, Mar 20, 2017, 4:55 AM UTC

blojayble wrote: post #24

Any recommendations for a book focused on AI in game development?

I've got a book called "Game Programming Patterns" by Robert Nystrom which goes into this. It's not advanced, but it's very good.

Re: Ask HN: Best books on AI?

#94

Post by thedailymail » Mon, Mar 20, 2017, 7:43 AM UTC

deepnet wrote: post #34

arihant wrote: post #26

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…

Sutton & Barto's Reinforment Learning complete this triumvirate https://webdocs.cs.ualberta.ca/~sutton/book/the-book-2nd.htm... David Silver's Reinforcement Course is based on Sutton & Barto https://www.youtube.com/watch?v=2pWv7GOvuf0

For whatever reason, Sutton's was the first serious book I read in any area of AI. The balance between explaining the history, the concepts and the code is handled really well.

Re: Ask HN: Best books on AI?

#95

Post by pvinis » Tue, Mar 21, 2017, 1:48 PM UTC

nextos wrote: post #84

pvinis wrote: post #58

Earlier quoted context omitted.

Art of Prolog was over of the best books I've read. As Prolog itself is one of my favorite languages. I wish there were more of both.

CTM by Van Roy & Haridi?

I will check it out. Thanks.