Here are 100 books that Deep Learning fans have personally recommended if you like
Deep Learning.
Shepherd is a community of 12,000+ authors and super readers sharing their favorite books with the world.
I’ve been working in machine learning for about a decade. I’ve always been more interested in applied than theoretical problems and while blogs and MOOCs (Massive Online Open Courses) are a great way to learn, for certain deep topics only a book would do. I also teach at University of Oxford, University of Birmingham, and various FTSE100 companies. My machine learning has exposed me to many fascinating problems—from leading my own ML-focused startup through Y Combinator—to working at various companies as a consultant. I think there is currently no great curriculum for the practitioners really wanting to apply deep learning in practical cases, so I have given it my best shot.
This is a fantastic book to get you started. It is written by the author of a leading deep learning framework Keras, which makes even Tensorflow very easy to use. Chollet is a true leader of the deep learning craft and the Manning team always does an excellent job of forcing authors to make the subject matter accessible. Highly recommended!
"The first edition of Deep Learning with Python is one of the best books on the subject. The second edition made it even better." - Todd Cook
The bestseller revised! Deep Learning with Python, Second Edition is a comprehensive introduction to the field of deep learning using Python and the powerful Keras library. Written by Google AI researcher Francois Chollet, the creator of Keras, this revised edition has been updated with new chapters, new tools, and cutting-edge techniques drawn from the latest research. You'll build your understanding through practical examples and intuitive explanations that make the complexities of deep learning…
I’ve been working in machine learning for about a decade. I’ve always been more interested in applied than theoretical problems and while blogs and MOOCs (Massive Online Open Courses) are a great way to learn, for certain deep topics only a book would do. I also teach at University of Oxford, University of Birmingham, and various FTSE100 companies. My machine learning has exposed me to many fascinating problems—from leading my own ML-focused startup through Y Combinator—to working at various companies as a consultant. I think there is currently no great curriculum for the practitioners really wanting to apply deep learning in practical cases, so I have given it my best shot.
Jeremy Howard is the lead author and has always been a world-class educator. This book is based on his fast.ai course, which has managed to splice all rigor, simplicity, and cutting edge techniques into one course. It also uses its custom fast.ai framework built on PyTorch, which is the dominant language for researchers. This book is very practically oriented and gets you off the ground very quickly with your own projects!
Deep learning is often viewed as the exclusive domain of math PhDs and big tech companies. But as this hands-on guide demonstrates, programmers comfortable with Python can achieve impressive results in deep learning with little math background, small amounts of data, and minimal code. How? With fastai, the first library to provide a consistent interface to the most frequently used deep learning applications.
Authors Jeremy Howard and Sylvain Gugger, the creators of fastai, show you how to train a model on a wide range of tasks using fastai and PyTorch. You'll also dive progressively further into deep learning theory to…
I’ve been working in machine learning for about a decade. I’ve always been more interested in applied than theoretical problems and while blogs and MOOCs (Massive Online Open Courses) are a great way to learn, for certain deep topics only a book would do. I also teach at University of Oxford, University of Birmingham, and various FTSE100 companies. My machine learning has exposed me to many fascinating problems—from leading my own ML-focused startup through Y Combinator—to working at various companies as a consultant. I think there is currently no great curriculum for the practitioners really wanting to apply deep learning in practical cases, so I have given it my best shot.
While technically not about deep learning, this book is fantastic for those interested in pursuing applied or practical machine learning problems. While the central thesis of a topic can be reduced to “Frequently, models are valuable simply by reducing uncertainty,” it is definitely worth a read as there’s a lot of deep thinking in this book!
Now updated with new measurement methods and new examples, How to Measure Anything shows managers how to inform themselves in order to make less risky, more profitable business decisions This insightful and eloquent book will show you how to measure those things in your own business, government agency or other organization that, until now, you may have considered "immeasurable," including customer satisfaction, organizational flexibility, technology risk, and technology ROI. * Adds new measurement methods, showing how they can be applied to a variety of areas such as risk management and customer satisfaction * Simplifies overall content while still making the…
I’ve been working in machine learning for about a decade. I’ve always been more interested in applied than theoretical problems and while blogs and MOOCs (Massive Online Open Courses) are a great way to learn, for certain deep topics only a book would do. I also teach at University of Oxford, University of Birmingham, and various FTSE100 companies. My machine learning has exposed me to many fascinating problems—from leading my own ML-focused startup through Y Combinator—to working at various companies as a consultant. I think there is currently no great curriculum for the practitioners really wanting to apply deep learning in practical cases, so I have given it my best shot.
This book is a fantastic intro to someone who really wants to intuitively understand deep learning. It can help you clear up things where you are stuck or simply if you’re having trouble explaining parts of your algorithm to your business stakeholders. It is also a really good preparation if you want a really solid, practical basis to come up with new tweaks or types of models.
Artificial Intelligence is the most exciting technology of the century, and Deep Learning is, quite literally, the "brain" behind the world's smartest Artificial Intelligence systems out there.
Grokking Deep Learning is the perfect place to begin the deep learning journey. Rather than just learning the "black box" API of some library or framework, readers will actually understand how to build these algorithms completely from scratch.
Key Features: Build neural networks that can see and understand images Build an A.I. that will learn to defeat you in a classic Atari game Hands-on Learning
Written for readers with high school-level math and…
My passion for generative AI first ignited in 2016 when I spoke about it at a conference, and ever since then, I can’t stop! I've created an online course, a newsletter and even wrote a book to spread knowledge on this groundbreaking technology. As an instructor, I empower others to explore the boundless potential of generative AI applications. Day in day out, I assist clients in crafting their own generative AI solutions, tailoring them to their unique needs.
I absolutely love Nick Bostrom's book because it dives deep into the fascinating yet daunting future of artificial intelligence, a topic that resonates with my own work. Bostrom's exploration of how superintelligent AI could emerge and the profound risks it poses is both thought-provoking and essential reading for anyone curious about technology's trajectory.
His insights on the challenges of control and alignment really struck a chord with me, as they highlight the importance of designing AI systems that prioritize human values. This book not only raises critical questions but also inspires a sense of urgency to navigate the future responsibly, making it a personal favorite and a vital resource for anyone interested in the intersection of AI and ethics.
The human brain has some capabilities that the brains of other animals lack. It is to these distinctive capabilities that our species owes its dominant position. Other animals have stronger muscles or sharper claws, but we have cleverer brains.
If machine brains one day come to surpass human brains in general intelligence, then this new superintelligence could become very powerful. As the fate of the gorillas now depends more on us humans than on the gorillas themselves, so the fate of our species then would come to depend on the actions of the machine superintelligence.
As a child of the microcomputer revolution in the late 1970s, I’ve always been fascinated by the concept of a general-purpose machine that I could control. The deep learning revolution of 2010 or so, followed most recently by the advent of large language models like ChatGPT, has completely altered the landscape. It is now difficult to interpret the behavior of these systems in a way that doesn’t argue for intelligence of some kind. I’m passionate about AI because, decades after the initial heady claims made in the 1950s, AI has reached a point where the lofty promise is genuinely beginning to be kept. And we’re just getting started.
Goodfellow’s Deep Learning is a must in the field because it was the first. Prince’s new book is an essential follow-up to be up-to-date with the latest model types, including diffusion models (think Stable Diffusion or DALL-E), transformers (the heart of large language models), graph networks (reasoning over relationships), and reinforcement learning.
The math level is similar to what you’ll find in Goodfellow’s book.
An authoritative, accessible, and up-to-date treatment of deep learning that strikes a pragmatic middle ground between theory and practice.
Deep learning is a fast-moving field with sweeping relevance in today’s increasingly digital world. Understanding Deep Learning provides an authoritative, accessible, and up-to-date treatment of the subject, covering all the key topics along with recent advances and cutting-edge concepts. Many deep learning texts are crowded with technical details that obscure fundamentals, but Simon Prince ruthlessly curates only the most important ideas to provide a high density of critical information in an intuitive and digestible form. From machine learning basics to advanced…
As a child of the microcomputer revolution in the late 1970s, I’ve always been fascinated by the concept of a general-purpose machine that I could control. The deep learning revolution of 2010 or so, followed most recently by the advent of large language models like ChatGPT, has completely altered the landscape. It is now difficult to interpret the behavior of these systems in a way that doesn’t argue for intelligence of some kind. I’m passionate about AI because, decades after the initial heady claims made in the 1950s, AI has reached a point where the lofty promise is genuinely beginning to be kept. And we’re just getting started.
Woolridge presents the history of artificial intelligence from the point of view of an insider. This book is one of the few accounts of AI history presenting a measured perspective, one that has weathered more than one boom and bust cycle.
The book is nicely complemented by his recent series of lectures, which can be easily found on YouTube. I read Woolridge as saying, “Yes, something new has happened with the advent of large language models, but much work remains.”
From Oxford's leading AI researcher comes a fun and accessible tour through the history and future of one of the most cutting edge and misunderstood field in science: Artificial Intelligence
The somewhat ill-defined long-term aim of AI is to build machines that are conscious, self-aware, and sentient; machines capable of the kind of intelligent autonomous action that currently only people are capable of. As an AI researcher with 25 years of experience, professor Mike Wooldridge has learned to be obsessively cautious about such claims, while still promoting an intense optimism about the future of the field. There have been genuine…
As a child of the microcomputer revolution in the late 1970s, I’ve always been fascinated by the concept of a general-purpose machine that I could control. The deep learning revolution of 2010 or so, followed most recently by the advent of large language models like ChatGPT, has completely altered the landscape. It is now difficult to interpret the behavior of these systems in a way that doesn’t argue for intelligence of some kind. I’m passionate about AI because, decades after the initial heady claims made in the 1950s, AI has reached a point where the lofty promise is genuinely beginning to be kept. And we’re just getting started.
Artificial intelligence is, of necessity, an academic pursuit, at least initially. McCorduck’s book is her account of the history and development of AI. She was not a historian coming to events after the fact but a living witness. Her circle of friends included all the key figures, the people those of us who fell into AI later didn’t have the opportunity to know.
This book, personal and human, not technical and heavy, reveals the humanness of the process. Yes, artificial intelligence was the goal, but human intelligence (and frailty) were central to its emergence.
In the autumn of 1960, twenty-year-old humanities student Pamela McCorduck encountered both the fringe science of early artificial intelligence, and C. P. Snow's Two Cultures lecture on the chasm between the sciences and the humanities. Each encounter shaped her life. Decades later her lifelong intuition was realized: AI and the humanities are profoundly connected. During that time, she wrote the first modern history of artificial intelligence, Machines Who Think, and spent much time pulling on the sleeves of public intellectuals, trying in futility to suggest that artificial intelligence could be important. Memoir, social history, group biography of the founding fathers…
As a child of the microcomputer revolution in the late 1970s, I’ve always been fascinated by the concept of a general-purpose machine that I could control. The deep learning revolution of 2010 or so, followed most recently by the advent of large language models like ChatGPT, has completely altered the landscape. It is now difficult to interpret the behavior of these systems in a way that doesn’t argue for intelligence of some kind. I’m passionate about AI because, decades after the initial heady claims made in the 1950s, AI has reached a point where the lofty promise is genuinely beginning to be kept. And we’re just getting started.
Alan Turing’s 1936 paper “On Computable Numbers, with an Application to the Entscheidungsproblem” was foundational to the development of computer science. To this day, Turing machines, the theoretical computational devices imagined in Turing’s paper, are a research cornerstone as they embody the concept of “computable.” If a programming language can implement a Turing machine, then the language is deemed Turing complete and is, therefore, general-purpose enough to implement any algorithm.
Turing’s paper is readable, but Petzold’s book breaks it down in minute detail to explain the nomenclature and meaning behind Turing’s words. I believe all computer science students should study this paper, and you’ll be hard-pressed to find a more thorough review than the one presented in this book.
Programming Legend Charles Petzold unlocks the secrets of the extraordinary and prescient 1936 paper by Alan M. Turing
Mathematician Alan Turing invented an imaginary computer known as the Turing Machine; in an age before computers, he explored the concept of what it meant to be computable, creating the field of computability theory in the process, a foundation of present-day computer programming.
The book expands Turing's original 36-page paper with additional background chapters and extensive annotations; the author elaborates on and clarifies many of Turing's statements, making the original difficult-to-read document accessible to present day programmers, computer science majors, math geeks,…
My passion for generative AI first ignited in 2016 when I spoke about it at a conference, and ever since then, I can’t stop! I've created an online course, a newsletter and even wrote a book to spread knowledge on this groundbreaking technology. As an instructor, I empower others to explore the boundless potential of generative AI applications. Day in day out, I assist clients in crafting their own generative AI solutions, tailoring them to their unique needs.
While it’s not the newest tech, I love that it covers the essential groundwork that sparked the modern AI revolution. I personally think its perfect for engineers and data scientists. It's also a great precursor to my book, giving you the strong foundation you need before diving into the next wave of AI advancements.
Generative modeling is one of the hottest topics in AI. It's now possible to teach a machine to excel at human endeavors such as painting, writing, and composing music. With this practical book, machine-learning engineers and data scientists will discover how to re-create some of the most impressive examples of generative deep learning models, such as variational autoencoders,generative adversarial networks (GANs), encoder-decoder models and world models.
Author David Foster demonstrates the inner workings of each technique, starting with the basics of deep learning before advancing to some of the most cutting-edge algorithms in the field. Through tips and tricks, you'll…
