Conflict between humans and machines is seen as inevitable and its outcome all too predictable.In this groundbreaking book, distinguished AI researcher Stuart Russell argues that this scenario can be avoided, but only if we rethink AI from the ground up. Russell begins by exploring the idea of intelligence in humans and in machines. He describes the near-term benefits we can expect, from intelligent personal assistants to vastly accelerated scientific research, and outlines the AI breakthroughs that still have to happen before we reach superhuman AI. He also spells out the ways humans are already finding to misuse AI, from lethal autonomous weapons to viral sabotage.If the predicted breakthroughs occur and superhuman AI emerges, we will have created entities far more powerful than ourselves. How can we ensure they never, ever, have power over us? Russell suggests that we can rebuild AI on a new foundation, according to which machines are designed to be inherently uncertain about the human preferences they are required to satisfy. Such machines would be humble, altruistic, and committed to pursue our objectives, not theirs. This new foundation would allow us to create machines that are provably deferential and provably beneficial.In a 2014 editorial co-authored with Stephen Hawking, Russell wrote, "Success in creating AI would be the biggest event in human history. Unfortunately, it might also be the last." Solving the problem of control over AI is not just possible; it is the key that unlocks a future of unlimited promise.

    This long-awaited revision contains changes throughout the text. There are new implementations of most of the major programming systems in the book, including the interpreters and compilers, and the authors have incorporated many small changes that reflect their experience teaching the course at MIT since the first edition was published. A new theme has been introduced that emphasizes the central role played by different approaches to dealing with time in computational models: objects with state, concurrent programming, functional programming and lazy evaluation, and nondeterministic programming. There are new example sections on higher-order procedures in graphics and on applications of stream processing in numerical programming, and many new exercises. In addition, all the programs have been reworked to run in any Scheme implementation that adheres to the IEEE standard.

    It is the basis for a new approach to artificial intelligence that aims to program computers to use example data or past experience to solve a given problem. In this volume in the MIT Press Essential Knowledge series, Ethem Alpayd�n offers a concise and accessible overview of the new AI. This expanded edition offers new material on such challenges facing machine learning as privacy, security, accountability, and bias. Alpayd�n, author of a popular textbook on machine learning, explains that as Big Data has gotten bigger, the theory of machine learning--the foundation of efforts to process that data into knowledge--has also advanced. He describes the evolution of the field, explains important learning algorithms, and presents example applications. He discusses the use of machine learning algorithms for pattern recognition; artificial neural networks inspired by the human brain; algorithms that learn associations between instances; and reinforcement learning, when an autonomous agent learns to take actions to maximize reward. In a new chapter, he considers transparency, explainability, and fairness, and the ethical and legal implications of making decisions based on data.

    With this long-awaited revision, the authors continue to present the theory in a concise and straightforward manner, now with an eye out for the practical applications. They have revised this book to make it more accessible to today's students, including the addition of more material on writing proofs, more figures and pictures to convey ideas, side-boxes to highlight other interesting material, and a less formal writing style. Exercises at the end of each chapter, including some new, easier exercises, help readers confirm and enhance their understanding of the material. *NEW! Completely rewritten to be less formal, providing more accessibility to todays students. *NEW! Increased usage of figures and pictures to help convey ideas. *NEW! More detail and intuition provided for definitions and proofs. *NEW! Provides special side-boxes to present supplemental material that may be of interest to readers. *NEW! Includes more exercises, including many at a lower level. *NEW! Presents program-like notation for PDAs and Turing machines. *NEW! Increas

    Highly recommended for graduate-level libraries.' ChoiceThis highly successful text, which first appeared in the year 1972 and has continued to be popular ever since, has now been brought up-to-date by incorporating the remarkable developments in the field of 'phase transitions and critical phenomena' that took place over the intervening years. This has been done by adding three new chapters (comprising over 150 pages and containing over 60 homework problems) which should enhance the usefulness of the book for both students and instructors. We trust that this classic text, which has been widely acclaimed for its clean derivations and clear explanations, will continue to provide further generations of students a sound training in the methods of statistical physics.

    Each chapter is relatively self-contained and can be used as a unit of study. The algorithms are described in English and in a pseudocode designed to be readable by anyone who has done a little programming. The explanations have been kept elementary without sacrificing depth of coverage or mathematical rigor.

    Mitchell covers the field of machine learning, the study of algorithms that allow computer programs to automatically improve through experience and that automatically infer general laws from specific data.