Dive into Deep Learning

by Aston Zhang, Zachary C. Lipton, Mu Li

Just a few years ago, there were no legions of deep learning scientists developing intelligent products and services at major companies and startups. When the youngest among us (the authors) entered the field, machine learning did not command headlines in daily newspapers. Our parents had no idea what machine learning was, let alone why we might prefer it to a career in medicine or law. Machine learning was a forward-looking academic discipline with a narrow set of real-world applications. And those applications, e.g., speech recognition and computer vision, required so much domain knowledge that they were often regarded as separate areas entirely for which machine learning was one small component. Neural networks then, the antecedents of the deep learning models that we focus on in this book, were regarded as outmoded tools.

In just the past five years, deep learning has taken the world by surprise, driving rapid progress in fields as diverse as computer vision, natural language processing, automatic speech recognition, reinforcement learning, and statistical modeling. With these advances in hand, we can now build cars that drive themselves with more autonomy than ever before (and less autonomy than some companies might have you believe), smart reply systems that automatically draft the most mundane emails, helping people dig out from oppressively large inboxes, and software agents that dominate the worldʼs best humans at board games like Go, a feat once thought to be decades away. Already, these tools exert ever-wider impacts on industry and society, changing the way movies are made, diseases are diagnosed, and playing a growing role in basic sciences—from astrophysics to biology.

Genres: Artificial Intelligence, Computer Science, Technology, Textbooks, Engineering, Programming, Technical

979 pages, ebook

Published September 18, 2020

Reviews

[Michał · Rating 4 out of 5]

The book is provided for free and continually updated by the authors and other contributors at https://d2l.ai

[Raj · Rating 3 out of 5]

3.5/5. It's an up-to-date and gentle survey covering a wide range of deep learning topics. Each topic has a mix of math and implementation. I found the math sections to be more useful: there is a good balance of rigor vs. intuition. I did not find the implementations useful as they relied on a custom library. Since the book is open source, a reader can easily contribute a fix by opening a PR.

[Nicky · Rating 5 out of 5]

While many other books fail in combining theory and practical implementation, this book thrives at exactly that. The D2L package might take some getting used to, but once you have seen an example or two the remaining code snippets are generally intuitive and truly help in understanding the accompanying theory. Great read!

[Linh Vu · Rating 4 out of 5]

A gentle introduction for beginners but lacks the rigor of Mathematics and deep understanding. Still, it's a good start: enough to know the field but requires more effort and other materials to understand and use the concepts effectively.

[Curious Nomad · Rating 5 out of 5]

After trudging through the 1100 pages of this mammoth, I can finally say that I know deep learning 🙂

P.S. The exercises will bake the shit out of you. You will start worshipping Lord GPT if you haven't already.

[Phan Hoang · Rating 4 out of 5]

This book is very simple for beginner who put first step in deep learning field. It explain clearly basis thing from simple model such as linear regression, logistic regression to complex model as NN, CNN or even Transformer.

[Tulip · Rating 4 out of 5]

good but not great.

[Ivan · Rating 5 out of 5]

Bite sized chapters, digestible practice problems (paper maths + plenty of coding) and a lively online community