Y Hacker News Books
Buy on Amazon4.3 out of 5, 2,395 ratings on Amazon

#94 of 2,629 all-time

Deep Learning

Ian Goodfellow, Yoshua Bengio, Aaron Courville

47 people recommended it in 14 threads, 2016–2025.

2 commenters pushed back on it — worth reading the threads.

What people on Hacker News said

ericjang
My favorite aspect of this book is that it provides a graphical models interpretation of DL methods, which is the most powerful perspective we have right now to reason about model design (instead of some large black box function that we train end-to-end without knowing what's in between).

on HN, 2016

ericjang
If you understand the models here, you should be able to understand the design choices made in more complex architectures.

on HN, 2016

mjw
It's a language you need to learn, especially if you want to try and get to the bottom of how and why aspects of deep learning work the way they do.

on HN, 2016

guiambros
"Deep Learning" - by Goodfellow and Bengio. Just started, but really liking it.

on HN, 2016

sherjilozair
Part of the problem in writing a deep learning book, is that very little that warrants being in a book, is actually known.

on HN, 2016

And on Amazon

Excellent book, possibly currently unique in coverage of latest ideas

This book is possibly currently unique in its coverage of the latest ideas in the field of deep learning -- and it is a very convenient and good survey of fundamental concepts (linear algebra, optimization, performance metrics, activation function types), different network types (multi-layer perceptron, convolutional neural networks, and recurrent neural networks), practical considerations (data set, training and validation, implementation), and applications (comments on existing real-world/commercial uses). …

0x00000000:00000000 · verified purchase · 5/5

A Classic in Deep Learning

A comprehensive and rigorous introduction to deep learning from the pioneers of the field. It provides a strong theoretical foundation while also covering the key concepts behind modern neural networks. It's more of a textbook than a casual read, but an invaluable reference for students, researchers, and practitioners alike.

Amazon Customer · verified purchase · 5/5

The definitive guide to becoming a researcher in the field

This is not a coding book. I see a lot of negative reviews around the expectation that this book would teach the reader how to quickly build machine learning systems and write code. This book is not for that audience. If you just want to build applications, don't worry about how deep learning works. It's akin to needing to understand how an engine works just to drive a car. If you are looking for a coding resource, try: https://www.amazon.com/Hands-Machine-Learning-Scikit-Learn-TensorFlow/dp/1492032646/ref=sr_1_4?keywords=machine+learning+tensorflow&qid=1579608765&sr=8-4 . …

Zygerian99 · verified purchase · 5/5

Where it comes up