Russell and Norvig: AI: A Modern Approach
Metadata
Title: Artificial Intelligence: A Modern Approach
Authors: Stuart Russell and Peter Norvig
Publication Year: 2021
Publisher: Pearson
Summary
An overview of the field of AI, using the unifying theme of an intelligent agent. See the summary of approach quote below.
The structure of the book is:
I. Artificial Intelligence - history and intro to the main theme of intelligent agents
II. Problem-solving - search problems, constraint satisfaction problems, adversarial search
III. Knowledge, Reasoning, Planning - Logic and logical agents, knowledge representation, automated planning
IV. Uncertain knowledge and reasoning - Quantifying uncertainty, probabilistic reasoning, decisions
V. Machine Learning - induction, knowledge in learning, deep learning, reinforcement learning
VI. Communicating, perceiving, acting - NLP, Deep learning for NLP, robotics, computer vision
VII. Conclusion - philosophy and future
Key Quotes
Summary of approach
We define AI as the study of agents that receive percepts from the environment and perform actions. Each such agent implements a function that maps percept sequences to actions, and we cover different ways to represent these functions, such as reactive agents, real-time planners, decision-theoretic systems, and deep learning systems. We emphasize learning both as a construction method for competent systems and as a way of extending the reach of the designer into unknown environments. We treat robotics and vision not as independently defined problems, but as occurring in the service of achieving goals. We stress the importance of the task environment in determining the appropriate agent design.
Preface, p. 8