For your category 2 book I would recommend: The Master Algorithm: How the Quest for the Ultimate Learning Machine https://www.goodreads.com/book/show/24612233-the-master-algo... (https://www.goodreads.com/book/show/24612233-the-master-algorithm) What I like about this book is that it covers the various ML camps. Not just Deep Learning, but the Baysean approach as well.
FROM THE HN SHELF
The Master Algorithm
Pedro Domingos
Computing · A BOOKTypographic jacket · original cover not fetched
FROM THE SHARED SHELF · 2006–2026 SAMPLE
The Master Algorithm
8 readers recommend it across 6 discussions
Topics are model-inferred labels.
Keep it on your reading list
THE WORD OF MOUTH
What made it worth passing on?
Original Hacker News comments, in the readers’ own words.
Type 1: Not sure. Type 2: The Master Algorithm by Pedro Domingos
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.
Also recommended in this reply
Bhagvad Gita (as it is) - A.C. Bhaktivedanta Swami Prabhupada Not just a spiritual book, more like the guiding principles that anyone, starting something new, could use. The Idea Factory: Bell Labs and the Great Age of American Innovation - Jon Gertner Bell Labs, the RnD wing of AT&T-was the best laboratory for new ideas in the world. The book tells a story about the life and work of a small group of brilliant people - Mervin Kelly, Bill Shockley, Claude Shannon, John Pierce, and Bill Baker. Peak - Anders Ericsson and Robert Pool You must have heard this a 1000 times - "you can do this", the book is about - "yes, and this is how" The master algorithm - Pedro Domingos Book details out the philosophies of various schools of thought in AI - deep learning, bayesian, genetic, reasoning - in a very simple language. What technology wants - Kevin Kelly Technology is a living organism and there are patterns to the technology evolution, not unlike the organic evolution.
Also recommended in this reply
Here are the best books I've read over the last few months: - Lost and Founder - the founder of Moz shares his advice and experience from building a 40M/year company. I found the things he says about building a startup extremely insightful and practically useful. Reading it feels like having a dinner with a friend who shares with you the things he has learned in a very honest, down to earth way. Highly recommend it. - Rationality from AI to Zombies - probably the most influential book I've read in my life, profoundly changed the way I think. It's a collection of LessWrong essays on science and rationality. (recently they've released an an audio version by the way). - "A Short History of Nearly Everything" and "Our Mathematical Universe" - two general popular science books I'm enjoying a lot. Haven't finished reading them yet, but so far they're brilliant(and very easy to understand, authors do an amazing job explaining complicated things in a simple, accessible way).…
Also recommended in this reply
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.…
Also recommended in this reply
Prisoners of Geography - Tim Marshall The Revenge of Geography - Robert D. Kaplan Prisoner's Dilemma - William Poundstone The Master Algorithm - Pedro Domingos Zero-Sum Future - Gideon Rachman The End of History and the Last Man - Francis Fukuyama Entanglement - Amir Aczel
Also recommended in this reply
The Master Algorithm by Pedro Domingos
Not sure about "significantly affected how I think", but here are a couple of the standouts from 2015 that come to mind: The First World War: A Complete History Predictable Revenue Superforecasting The Master Algorithm Natural Born Heroes
Also recommended in this reply