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…
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…
It’s been fantastic to work in computer vision, especially when it is used to build biometric systems. I and my 80 odd PhD students have pioneered systems that recognise people by the way they walk, by their ears, and many other new things too. To build the systems, we needed computer vision techniques and architectures, both of which work with complex real-world imagery. That’s what computer vision gives you: a capability to ‘see’ using a computer. I think we can still go a lot further: to give blind people sight, to enable better invasive surgery, to autonomise more of our industrial society, and to give us capabilities we never knew we’d have.
The advances of deep learning have been awesome, and fast. It’s been hard for the textbooks to keep up, so it’s good to include one that describes the advances and state of art very well. It seems appropriate that it’s edited by two leading researchers who are Roy – who described computer vision systems implementations in a long series of excellent books – and Matt, whose work on face recognition revolutionised and transformed the progress of face recognition in the 1990s. This book gives you an image of where we are now in computer vision, and where we are going.
Advanced Methods and Deep Learning in Computer Vision presents advanced computer vision methods, emphasizing machine and deep learning techniques that have emerged during the past 5-10 years. The book provides clear explanations of principles and algorithms supported with applications. Topics covered include machine learning, deep learning networks, generative adversarial networks, deep reinforcement learning, self-supervised learning, extraction of robust features, object detection, semantic segmentation, linguistic descriptions of images, visual search, visual tracking, 3D shape retrieval, image inpainting, novelty and anomaly detection.
This book provides easy learning for researchers and practitioners of advanced computer vision methods, but it is also suitable as…
Arshin Adib-Moghaddam is Professor in Global Thought and Comparative Philosophies at SOAS University of London and Fellow of Hughes Hall, University of Cambridge. Among over a dozen honorary appointments all over the world, Adib-Moghaddam is the inaugural Director of the SOAS Centre for AI Futures.
A fantastic expose about the perils of Artificial Intelligence written with clear passion for a just and equitable AI future.
This book serves as an introduction into AI’s deep learning technology and its political effects. In easily digestible prose, it charters the ways that AI impacts society and how it feeds into various social predicaments, such as the rise of right-wing movements in Europe and North America.
Artificial Intelligence (AI) is everywhere, yet it causes damage to society in ways that can't be fixed. Instead of helping to address our current crises, AI causes divisions that limit people's life chances, and even suggests fascistic solutions to social problems. This book provides an analysis of AI's deep learning technology and its political effects and traces the ways that it resonates with contemporary political and social currents, from global austerity to the rise of the far right. Dan McQuillan calls for us to resist AI as we know it and restructure it by prioritising the common good over algorithmic…
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.
Deep learning burst on the scene in 2012 with the success of the AlexNet model in the ImageNet competition. The first comprehensive deep learning text was this one, released in 2016.
It’s almost a necessity for deep learning practitioners, but it is not for beginners. Think of it as a graduate-level text. After eight years, some portions read as slightly dated, but the essentials have not changed.
An introduction to a broad range of topics in deep learning, covering mathematical and conceptual background, deep learning techniques used in industry, and research perspectives.
“Written by three experts in the field, Deep Learning is the only comprehensive book on the subject.” —Elon Musk, cochair of OpenAI; cofounder and CEO of Tesla and SpaceX
Deep learning is a form of machine learning that enables computers to learn from experience and understand the world in terms of a hierarchy of concepts. Because the computer gathers knowledge from experience, there is no need for a human computer operator to formally specify all…
Coming from two very different backgrounds gives Dean and I a unique ‘view’ of a topic that we are both hugely passionate about: artificial intelligence. Our work together has gifted us a broader perspective in terms of understanding the development of and the philosophy beneath what is coined as artificial intelligence today and where we truly stand in terms of its potential for good – and evil. Our book list is intended to provide a great starting point from where you can jump into this incredibly absorbing topic and draw your own conclusions about where the future might take us.
We found this book to be an eye-opening exploration of the revolutionary merging of artificial intelligence and biotechnology. Brian Hilbush expertly guided us through the cutting-edge advancements that are transforming drug discovery and therapeutics without being too technical or scientific in his use of language.
We found Hilbush’s story to be a fascinating breakdown of how AI and deep learning are revolutionizing medicine, with some great insights into the rise of data science in healthcare, groundbreaking biotech innovations, and the exciting startup landscape shaping the industry's future.
Learn how AI and data science are upending the worlds of biology and medicine
In Silico Dreams: How Artificial Intelligence and Biotechnology Will Create the Medicines of the Future delivers an illuminating and fresh perspective on the convergence of two powerful technologies: AI and biotech. Accomplished genomics expert, executive, and author Brian Hilbush offers readers a brilliant exploration of the most current work of pioneering tech giants and biotechnology startups who have already started disrupting healthcare. The book provides an in-depth understanding of the sources of innovation that are driving the shift in the pharmaceutical industry away from serendipitous therapeutic…
I’ve been a geeky kid all my life. (I don’t think I’ve quite grown up yet.) Born in the 1970s, my childhood was a wonderful playground of building robots and software. I was awarded one of the early degrees in AI, and a PhD in genetic algorithms. I’ve since spent 25 years exploring how to make computers think, build, invent, compose… and I’ve also spent 20 years writing popular science books. I’m lucky enough to be a Professor in one of the world’s best universities for Computer Science and Machine Learning: UCL, and I guess I’ve written two or three hundred scientific papers over the years. I still think I know nothing at all about real or artificial intelligence, but then does anyone?
I’ve not met Harry, but he seems to have a logical and sensible head on his shoulders. His writing is considered and grounded, which is exactly what you need when discussing the hype that forever seems to surround AI. This book is another look at this topic and finds yet more ways to explain to readers the difference between human intelligence and our algorithmic attempts at intelligence – which are frequently pretty stupid.
Recent startling successes in machine intelligence using a technique called 'deep learning' seem to blur the line between human and machine as never before. Are computers on the cusp of becoming so intelligent that they will render humans obsolete? Harry Collins argues we are getting ahead of ourselves, caught up in images of a fantastical future dreamt up in fictional portrayals. The greater present danger is that we lose sight of the very real limitations of artificial intelligence and readily enslave ourselves to stupid computers: the 'Surrender'.
By dissecting the intricacies of language use and meaning, Collins shows how far…
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 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.
There are three types of machine learning books — books written for people who want to become machine learning engineers, books written for people who want to become machine learning researchers, and books written for business executives. Reading a book written for researchers or executives can be a frustrating experience if you are a software engineer, social scientist, or mechanical engineer who wants to learn machine learning and get an ML job in the industry.
If you are a coder who wants to become an ML engineer, you have got to learn machine learning concepts, but you want to learn them in a practical way. You need a book that leads with intuition and shows you implementations with code. It has to do this without getting sidetracked into ML theory, getting mired in statistical concepts, or being so superficial that you don’t understand why the code works.…
Through a series of recent breakthroughs, deep learning has boosted the entire field of machine learning. Now, even programmers who know close to nothing about this technology can use simple, efficient tools to implement programs capable of learning from data. This practical book shows you how.
By using concrete examples, minimal theory, and two production-ready Python frameworks-Scikit-Learn and TensorFlow-author Aurelien Geron helps you gain an intuitive understanding of the concepts and tools for building intelligent systems. You'll learn a range of techniques, starting with simple linear regression and progressing to deep neural networks. With exercises in each chapter to help…
Coming from two very different backgrounds gives Dean and I a unique ‘view’ of a topic that we are both hugely passionate about: artificial intelligence. Our work together has gifted us a broader perspective in terms of understanding the development of and the philosophy beneath what is coined as artificial intelligence today and where we truly stand in terms of its potential for good – and evil. Our book list is intended to provide a great starting point from where you can jump into this incredibly absorbing topic and draw your own conclusions about where the future might take us.
Don't be fooled by the lack of a breezy narrative. This read is a dense exploration of deep learning's impact and is certainly not an ‘easy read’ by any measure, but its rewards are substantial.
Buckner delves deep into the philosophical debates surrounding AI, particularly the clash between empiricism and rationalism. Through this lens, he develops a "moderate empiricism" that sheds light on the true potential and limitations of AI. While the book demands focus, we found the payoff to be significant.
This book provides a framework for thinking about foundational philosophical questions surrounding the use of deep artificial neural networks ("deep learning") to achieve artificial intelligence. Specifically, it links recent breakthroughs to classic works in empiricist philosophy of mind. In recent assessments of deep learning's potential, scientists have cited historical figures from the philosophical debate between nativism and empiricism, which concerns the origins of abstract knowledge. These empiricists were faculty psychologists; that is, they argued that the extraction of abstract knowledge from experience involves the active engagement of psychological faculties such as perception, memory, imagination, attention, and empathy. This book explains…
