Here are 63 books that Deep Learning fans have personally recommended if you like
Deep Learning.
Shepherd is a community of 10,000+ authors and super readers sharing their favorite books with the world.
Shepherd is reader supported. When you buy books, we may earn an affiliate commission.
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…
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,…
I have been building real-time, production machine learning models for over 20 years. My book, and my book recommendations, are informed by that experience. I have a lot of empathy for people who are new to machine learning because I’ve taught courses on the topic. I founded the Advanced Solutions Lab at Google where we helped data scientists working for Google Cloud customers (who already knew ML) become ML engineers capable of building reliable ML models. The first two are the books I’d recommend today to newcomers and the last three to folks attending the ASL.
This recommendation is a bit of a cheat — I’m not recommending this exact book, but one of the books in the series that this book is part of.
Once you have the first two books under your belt, you’ll know how to solve ML problems. But you will keep reinventing the wheel. What you need next is a book on common “ML tricks” — best practices and common techniques when doing ML in production.
The problem is that these tricks are specific to the type of data that you will be processing. If you are going to be processing images or time series, read the corresponding books in the same series instead.
Many books and courses tackle natural language processing (NLP) problems with toy use cases and well-defined datasets. But if you want to build, iterate, and scale NLP systems in a business setting and tailor them for particular industry verticals, this is your guide. Software engineers and data scientists will learn how to navigate the maze of options available at each step of the journey.
Through the course of the book, authors Sowmya Vajjala, Bodhisattwa Majumder, Anuj Gupta, and Harshit Surana will guide you through the process of building real-world NLP solutions embedded in larger product setups. You'll learn how to…
I started my career in neuroscience. I wanted to understand brains. That is still proving difficult, and somewhere along the way, I realized my real motivation was to build things, and I wound up working in AI. I love the elegance of mathematical models of the world. Even the simplest machine learning model has complex implications, and exploring them is a joy.
This is the practical book that best accompanies my book (which is more about the underlying ideas.)
If you want a book that will show you how deep learning systems are built in practice, then this is the best place to start. It’s full of code snippets that translate between theory and building real systems.
Deep learning has revolutionized pattern recognition, introducing tools that power a wide range of technologies in such diverse fields as computer vision, natural language processing, and automatic speech recognition. Applying deep learning requires you to simultaneously understand how to cast a problem, the basic mathematics of modeling, the algorithms for fitting your models to data, and the engineering techniques to implement it all. This book is a comprehensive resource that makes deep learning approachable, while still providing sufficient technical depth to enable engineers, scientists, and students to use deep learning in their own work. No previous background in machine learning…
