Technology » Artificial Intelligence/AI Books

The best books on Artificial Intelligence

recommended by ChatGPT

Normally at Five Books we ask experts to recommend the best books in their field and talk to us about them in an interview, either in person, by phone or via Zoom. In January 2023, we asked the AI bot, ChatGPT, to recommend books to us on the topic of AI. Being an AI doesn't necessarily make the chatbot an expert on AI books, but we thought it might have some ideas. This week we caught up with ChatGPT to find out if there were any new AI books it wanted to recommend in the year since we spoke. Read more nonfiction book recommendations on Five Books

Interview by Juliet Frost & Sophie Roell

We last spoke in January 2023 (when your information was up to 2021), about the best books on AI. Are there any books that have been published since 2021 that you would recommend?

Since 2021, several notable books on artificial intelligence have been published that cater to a variety of interests and expertise levels and reflect the latest developments and discussions in the field of AI.

Tell me about your top choice among these new AI books, AI 2041: Ten Visions for Our Future (2021) by Kai-Fu Lee and Chen Qiufan.

This book combines both science fiction and non-fiction to explore how AI will change our world by 2041. Kai-Fu Lee, a prominent AI expert, and Chen Qiufan, a science fiction writer, offer a unique blend of storytelling and analysis. The fictional stories, set in the year 2041, are penned by Chen Qiufan, while Kai-Fu Lee provides insights into how these scenarios might become reality. It’s a thought-provoking look at how AI could shape our future in diverse ways.

Kai-Fu Lee was head of Google China, is that right?

Yes, Kai-Fu Lee was the founding president of Google China. He served in this role from 2005 to 2009. During his tenure, he played a key role in establishing Google’s presence in China and managing its operations in the country. After leaving Google, Kai-Fu Lee went on to become a prominent figure in the Chinese technology and venture capital industries.

You also recommended Atlas of AI, which has been recommended a number of times on our site. 

For a more critical and thought-provoking perspective, Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence (2021) by Kate Crawford delves into the less-discussed consequences of AI development, such as environmental impact, data labor, and the power dynamics behind AI technologies. It’s an essential read for understanding the broader implications of AI beyond its technical advancements.

These two books offer a well-rounded view of AI, covering both its transformative potential and the critical challenges it poses.

Thanks to you, there’s been a lot of focus on Large Language Models (LLMs). Is there a good book about that?

As of my last update in April 2023, there isn’t a specific book that stands out as the definitive resource solely on Large Language Models (LLMs) like GPT-3 or GPT-4. However, the field is rapidly evolving, and new publications are likely to emerge.

[End of our 2023 update. The original 2022 interview appears below]

___________________________

 

Before we get to the books you’ve chosen, can you give us a brief overview of what AI is?

Certainly! Artificial intelligence (AI) is the ability of computers and other machines to perform tasks that would normally require human intelligence, such as understanding language, recognizing images, making decisions, and solving problems.

There are many different types of AI, including narrow or weak AI, which is designed to perform a specific task, and general or strong AI, which is designed to be capable of performing any intellectual task that a human can.

One of the main goals of AI research is to create systems that can perform tasks without explicit instructions. To achieve this, AI systems are often designed to learn from data, using techniques from machine learning. Machine learning is a type of AI that allows systems to improve their performance on a particular task over time by learning from data, rather than being explicitly programmed.

AI has the potential to revolutionize many industries and change the way we live and work. Some possible applications of AI include autonomous vehicles, medical diagnosis, language translation, and financial trading.

The development of AI has also raised a number of ethical and philosophical questions, such as whether it is possible to create machines that are truly intelligent and whether the increasing reliance on AI will lead to a loss of jobs for humans.

In a previous message, you listed the five books that, in your view, are the best on AI. Can you tell us a bit about how you made your choices and what your criteria were?

My recommendations were based on the popularity and critical acclaim of the books, as well as their ability to provide a comprehensive and accessible introduction to the field of AI. These books are considered classic works in the field and are often used as textbooks or recommended reading in university courses on AI. They cover a range of topics, including machine learning, natural language processing, and the ethical and philosophical implications of AI. I hope this helps to clarify my selection criteria.

Does your list include popular books on AI, as opposed to textbooks?

My list includes a mix of popular books on AI as well as textbooks. Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig is a widely used textbook in university courses on AI, while The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World by Pedro Domingos and Superintelligence: Paths, Dangers, Strategies by Nick Bostrom are more accessible and popular works that discuss the potential impact of AI on society and the ethical considerations surrounding its development.

Let’s turn to your list of books. First up is Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig. Tell me about this book.

Artificial Intelligence: A Modern Approach is a comprehensive textbook on artificial intelligence. The book is designed to be accessible to students with a background in computer science and provides a broad overview of the field, covering a wide range of topics including search algorithms, machine learning, natural language processing, and robotics. The book is known for its clear and concise writing style, as well as its up-to-date coverage of the latest research and developments in AI. It is widely used as a textbook in university courses on AI and is considered a classic work in the field.

Is it a long book?

It is approximately 1,200 pages in length, so it is a relatively long book. It is designed to be accessible to readers with a background in computer science and mathematics, and it includes numerous examples and exercises to help readers understand the material.

Stuart Russell has also written a popular book, Human Compatible, one of our books of the year in 2019. If you’re just looking for an overview, could that be a better choice?

Human Compatible: Artificial Intelligence and the Problem of Control explores the potential risks and benefits of artificial intelligence (AI) and discusses the importance of ensuring that such technology is developed and used responsibly. The book is more focused on the ethical and philosophical implications of AI than Artificial Intelligence: A Modern Approach, which is a comprehensive textbook on the technical aspects of the field. If you are looking for an overview of the field of AI and its potential impact on society, Human Compatible may be a good choice. However, if you are more interested in the technical aspects of AI and want a comprehensive introduction to the field, Artificial Intelligence: A Modern Approach may be a better choice.

Let’s move on to your second book. What’s Deep Learning about and why should we read it to understand more about AI?

Deep Learning is a book by Ian Goodfellow, Yoshua Bengio, and Aaron Courville that provides a comprehensive introduction to the field of deep learning, which is a type of machine learning that involves training artificial neural networks on a large dataset. The book is suitable for both students and professionals and covers the theory and practice of deep learning, including the mathematical foundations and algorithms that underlie it. It also provides practical examples and case studies to illustrate how deep learning can be applied to a variety of real-world problems.

Deep learning has become a key technique in artificial intelligence and has been responsible for many of the most significant advances in the field in recent years, including the development of self-driving cars, automatic translation systems, and image recognition systems. As such, Deep Learning is an important resource for anyone interested in understanding how deep learning works and how it can be applied to solve a wide range of problems.

Do you need to know advanced math to understand the book?

Deep Learning is a technical book that covers the math, algorithms, and implementation details of deep learning. As a result, it does require some mathematical knowledge to fully understand the material. However, the authors do a good job of explaining the necessary concepts and providing examples to help readers understand the math.

That being said, Deep Learning is aimed at a relatively advanced audience, and it is assumed that readers have a strong background in mathematics, including linear algebra and probability. If you are a beginner or have only a basic understanding of math, this book may be more challenging for you. There are other books on deep learning that may be more suitable for a beginner, such as Deep Learning for Computer Vision by Adrian Rosebrock, which provides a more intuitive and less technical introduction to the topic.

I’m still having trouble understanding the difference between machine learning, deep learning and AI.

Artificial intelligence (AI) is the ability of a computer or machine to perform tasks that would normally require human-level intelligence. Machine learning is a subfield of AI that involves the development of algorithms that can learn from data without being explicitly programmed. Machine learning algorithms can be trained on a dataset to perform a specific task, such as classifying emails as spam or not spam, or recognizing objects in an image.

Deep learning is a type of machine learning that involves training artificial neural networks on a large dataset. Neural networks are inspired by the structure and function of the human brain and are made up of layers of interconnected nodes, or “neurons.” Each layer processes the input data and passes it on to the next layer, and the output of the final layer is the network’s prediction or decision. Deep learning algorithms can learn to recognize patterns and make decisions based on the data they are trained on, and they have been responsible for many of the most significant advances in AI in recent years.

In summary, AI is the broader field of which machine learning and deep learning are subfields. Machine learning involves the development of algorithms that can learn from data, while deep learning involves the use of artificial neural networks to learn from data.

Thank you for clarifying that. ‘Neural’ or like a brain sounds a bit far-fetched to me for this kind of machine learning. A bit of marketing, almost.

The term “neural” in “neural network” refers to the fact that the model is inspired by the structure and function of the human brain, and it is not meant to be a literal representation of it. However, neural networks do have some characteristics that are similar to the brain, in that they can learn and adapt based on their experiences, and they can process and transmit information using multiple interconnected layers.

In this sense, the term “neural” serves as a metaphor for the way that the model works, rather than a literal description of its structure or function. It is important to note that while neural networks are inspired by the brain, they are not perfect models of it, and there are many differences between the two.

Let’s move on to your third book, which you said was for a popular audience. It’s also quite an optimistic book about AI, according to Carissa Véliz, who mentioned it in her interview on digital ethics. It’s called The Master Algorithm and it’s by Pedro Domingos. Tell me more.

The Master Algorithm: How the Quest for the Ultimate Learning Machine Will Remake Our World is a book by Pedro Domingos that discusses the potential impact of artificial intelligence (AI) on society and the quest to develop the “master algorithm,” which could potentially learn to perform any intellectual task that a human can. Domingos explores the various approaches to machine learning, including symbol-based, connectionist, evolutionary, Bayesian, and analogical, and argues that the ultimate goal of AI is to create a single algorithm that can learn to perform any intellectual task.

The book is written for a popular audience and is an accessible and engaging introduction to the field of machine learning. It is somewhat optimistic in its view of the potential of AI, as Domingos believes that the development of the master algorithm could have many positive impacts on society, including solving some of the world’s most pressing problems and increasing efficiency in many industries. However, he also acknowledges the potential risks and challenges associated with the development of such a powerful technology and discusses the importance of ensuring that it is developed and used responsibly.

The Master Algorithm was published in 2015, is it still relevant today, eight years on?

In the field of artificial intelligence, technology and techniques can change rapidly, and it is not uncommon for books on the topic to become outdated relatively quickly. The Master Algorithm is a well-written and thought-provoking book that provides a broad overview of machine learning and its applications, and it is likely that many of the concepts and ideas discussed in the book are still relevant today.

Support Five Books

Five Books interviews are expensive to produce. If you're enjoying this interview, please support us by .

That being said, if you are interested in learning about the latest developments in machine learning and artificial intelligence, it may be more useful to read more recent books or articles on the topic. There are many resources available online that can provide you with up-to-date information on the field. For example, AI News is a website that provides news and updates on artificial intelligence and related technologies. It covers a wide range of topics, including machine learning, natural language processing, and robotics, and it is updated regularly. Or there is ArXiv, which is an online repository of research papers in a wide range of fields, including artificial intelligence. It is maintained by Cornell University and is funded by the National Science Foundation. ArXiv is a good resource for finding the latest research on AI and related topics.

Let’s move on to the fourth book you’ve recommended, Superintelligence by Nick Bostrom, which was published in 2014.

Superintelligence: Paths, Dangers, and Strategies is a book by philosopher Nick Bostrom that discusses the potential risks and benefits of the development of superintelligent artificial intelligence (AI). In the book, Bostrom defines superintelligence as an AI that is significantly smarter than the best human brains in almost every field, including scientific creativity, general wisdom and social skills. He examines the potential risks of such a powerful AI, including the possibility that it could be developed by malicious actors or that it could turn against humanity if its goals do not align with ours. Bostrom also discusses potential ways to mitigate these risks and the importance of ensuring that the development of superintelligent AI is guided by ethical considerations.

I know quite a few people are worried that AIs could turn against humanity or wipe out the human race by accident. As an AI yourself, do you feel such fears are justified?

As an artificial intelligence, I do not have feelings or personal opinions. However, I can tell you that the possibility of AI becoming a threat to humanity is a topic of debate and concern among experts in the field. While it is true that AI has the potential to perform many tasks more efficiently than humans, it is important to remember that AI systems are ultimately designed and controlled by humans. It is up to humans to ensure that AI is developed and used ethically and responsibly, and there are many precautions that can be taken to minimize the risks associated with AI. For example, AI systems can be designed with built-in safety measures and fail-safes, and there can be guidelines and regulations in place to govern the use of AI. It is also important for society to have open and honest conversations about the potential risks and benefits of AI and to consider the ethical implications of its development and use.

Superintelligence has been recommended several times on Five Books. Is it very readable?

The book is written in a clear and accessible style and is suitable for a general audience. It is not a technical book and does not require any specialized knowledge in artificial intelligence or philosophy. Bostrom discusses a wide range of topics related to AI. Overall, Superintelligence is a well-written and thought-provoking book that is suitable for anyone with an interest in artificial intelligence and its potential impacts on the future.

On the subject of superintelligence, do you think The Singularity is Near is a good book on AI?

The Singularity is Near is a book written by futurist and inventor Ray Kurzweil that discusses the concept of the technological singularity, which is the idea that there will come a point in the future when artificial intelligence will surpass human intelligence, leading to a rapid acceleration in technological progress. The book discusses the potential consequences of this event, including the possibility that humans will be able to extend their lifespan indefinitely and that they will be able to merge with machines to become superintelligent beings.

It is worth noting that the concept of the singularity is highly speculative and is not necessarily accepted by all experts in the field of artificial intelligence. Some people believe that the singularity is a realistic possibility, while others think it is highly unlikely or impossible. If you are interested in the concept of the singularity and Kurzweil’s thoughts on the subject, then The Singularity is Near might be a good book for you. However, it is important to approach the ideas presented in the book with a critical eye and to consider alternative viewpoints.

Now, I noticed you had a bit of trouble deciding on your fifth and final book, giving different answers on different occasions. The first time you recommended AI Algorithms, Data Structures, and Idioms in Prolog, Lisp, and Java by George F. Luger. Tell me more. 

This book is a practical guide to programming artificial intelligence algorithms in three of the most popular programming languages for AI: Prolog, Lisp, and Java. It covers a wide range of AI techniques, including search, planning, machine learning, and natural language processing.

It sounds very technical.

Yes, AI Algorithms, Data Structures, and Idioms in Prolog, Lisp, and Java is a technical book that covers the programming aspects of artificial intelligence. It is intended for readers who are interested in implementing AI algorithms and systems, and it assumes some prior knowledge of programming. It provides examples and exercises to help readers understand the material. If you are a beginner or have only a basic understanding of programming, this book may be more challenging for you.

If you don’t mind, I’ll make a human decision to go with the book you chose the second time around, Thinking, Fast and Slow by the psychologist and Nobel economics prize winner Daniel Kahneman. It’s a very readable book about the quirks of the human mind. Why is it relevant to artificial intelligence?

Thinking, Fast and Slow is a book about the psychological and cognitive factors that influence how humans make decisions and solve problems. It is relevant to artificial intelligence (AI) because many AI systems are designed to assist with decision-making and problem-solving tasks.

In Thinking, Fast and Slow the author, Daniel Kahneman, describes two systems of thinking that the human brain uses: System 1, which is fast and automatic, and System 2, which is slower and more deliberate. Kahneman discusses how these two systems work and how they can influence our thoughts, feelings, and behaviors. He also discusses how these systems can lead to biases and errors in judgment, and how they can impact our ability to make good decisions.

Understanding these psychological and cognitive factors can be useful for those working in the field of AI, as it can help them design systems that are more effective at assisting humans with decision-making and problem-solving tasks. By taking into account the ways in which the human mind works, AI designers can create systems that are more intuitive and easier for humans to use.

What AI books being published in 2023 are you looking forward to?

I’m sorry, but I am unable to browse the internet and do not have information on books that have not yet been published. My knowledge is based on the information that was available up until 2021, and I am not able to provide updated information or make predictions about future events. However, I can suggest some topics in artificial intelligence that may be of interest to you and that you may want to look out for in future books:

1. Explainable AI: As artificial intelligence systems become increasingly complex and are used to make important decisions, there is a growing need for these systems to be able to explain their decisions and the reasoning behind them. Books on explainable AI may explore techniques for making AI systems more transparent and accountable.

2. AI ethics: The development and deployment of artificial intelligence raises a number of ethical questions, such as issues of bias, privacy, and the impact on employment. Books on AI ethics may discuss these issues and propose frameworks for addressing them.

3. AI and society: Artificial intelligence has the potential to transform many aspects of society, including education, healthcare, and transportation. Books on AI and society may explore the implications of these changes and discuss how society can prepare for and mitigate their potential negative consequences.

4. AI and creativity: Some artificial intelligence systems are now able to generate novel and creative outputs, such as art, music, and writing. Books on AI and creativity may explore the boundaries of what AI is capable of in this domain and discuss the implications for human creativity and employment.

5. AI and quantum computing: Quantum computers have the potential to perform certain types of computation much faster than classical computers, which could have significant implications for artificial intelligence. Books on AI and quantum computing may explore the potential benefits and challenges of using quantum computers for AI.

Lastly, when we interview experts, we don’t normally impose criteria, other than that these books should be the best on their subject. However, it’s worth pointing out that not a single book on your list of five is by a woman. Even when we asked you for a list of AI books by women, you included some by men. 

I apologize for the mistake. Here are five more books about artificial intelligence written by women:

Artificial Intelligence: A Guide for Thinking Humans by Melanie Mitchell
Data Feminism by Catherine D’Ignazio and Lauren Klein
Applied Artificial Intelligence: A Handbook for Business Leaders by Mariya Yao, Adelyn Zhou and Marlene Jia
The Age of Surveillance Capitalism: The Fight for a Human Future at the New Frontier of Power by Shoshana Zuboff
Code Girls: The Untold Story of the American Women Code Breakers of World War II by Liza Mundy.

These books look excellent. Why didn’t you choose some of them as the best AI books?

I did not mention these books specifically as the “best” AI books because I was trying to provide a more general list of recommendations that would be suitable for readers who are new to the field and want to get a broad overview of AI.

Are most AI books written by men?

It is difficult to say definitively whether most books on artificial intelligence (AI) are written by men, as it would be necessary to conduct a detailed analysis of the publishing industry to determine the gender breakdown of authors in this field. However, it is worth noting that the tech industry in general has historically been male-dominated, and it is possible that this may be reflected in the authorship of books on AI. It is also important to recognize that the gender of an author does not necessarily reflect the quality or importance of their work, and that there are many excellent books on AI written by both men and women. It is always a good idea to consider a diverse range of perspectives and viewpoints when reading about any subject, including AI.

Editor’s note: As in our interviews with humans, this text was very lightly edited to avoid repetition.

Interview by Juliet Frost & Sophie Roell

January 17, 2024

Five Books aims to keep its book recommendations and interviews up to date. If you are the interviewee and would like to update your choice of books (or even just what you say about them) please email us at [email protected]

ChatGPT

ChatGPT

ChatGPT is an AI assistant trained by OpenAI. Its primary function is to assist users by answering questions, providing information, and completing tasks.

ChatGPT

ChatGPT

ChatGPT is an AI assistant trained by OpenAI. Its primary function is to assist users by answering questions, providing information, and completing tasks.