Artificial Intelligence: A Modern Approach, Global Edition, 4th edition

Published by Pearson (29 July 2024) © 2024

  • Stuart Russell University of California at Berkeley
  • Peter Norvig
Products list

Access details

  • Instant access once purchased
  • Offline access via app

Features

  • Learn with videos and interactives*
  • Highlight-to-translate in 100+ languages
  • Practice with quizzes and flashcards
  • AI-powered study support*

*Available for some titles

Products list

Access details

  • Instant access once purchased
  • Offline access via app

Features

  • Learn with videos and interactives*
  • Highlight-to-translate in 100+ languages
  • Practice with quizzes and flashcards
  • AI-powered study support*

*Available for some titles

Title overview

Artificial intelligence is transforming how problems are solved across science, technology, business, and everyday life. Artificial Intelligence: A Modern Approach provides a comprehensive introduction to the theory and practice of AI, helping learners build a strong foundation while engaging with advanced topics shaping the field today. Concepts are introduced in an accessible way before progressing to mathematical and algorithmic detail, making it easier to understand how AI systems reason, learn, make decisions, and interact with the world. The content presents a unified view of AI, showing how key areas connect across modern applications and emerging developments.

Learners develop the knowledge and skills needed to understand, evaluate, and apply core AI concepts across a wide range of domains. Through topics including search, reasoning, machine learning, deep learning, natural language processing, robotics, and decision making, learners gain insight into how intelligent systems are designed and improved. Expanded coverage of causality, transfer learning, probabilistic programming, privacy, fairness, and safe AI helps learners engage with both technical and societal challenges. The broad scope supports deeper understanding while enabling learners to connect foundational principles with current AI technologies and future developments.

Table of contents

  • Chapter 1: Introduction
  • Chapter 2: Intelligent Agents
  • Chapter 3: Solving Problems by Searching
  • Chapter 4: Search in Complex Environments
  • Chapter 5: Constraint Satisfaction Problems
  • Chapter 6: Adversarial Search and Games
  • Chapter 7: Logical Agents
  • Chapter 8: First-Order Logic
  • Chapter 9: Inference in First-Order Logic
  • Chapter 10: Knowledge Representation
  • Chapter 11: Automated Planning
  • Chapter 12: Quantifying Uncertainty
  • Chapter 13: Probabilistic Reasoning
  • Chapter 14: Probabilistic Reasoning over Time
  • Chapter 15: Making Simple Decisions
  • Chapter 16: Making Complex Decisions
  • Chapter 17: Multiagent Decision Making
  • Chapter 18: Probabilistic Programming
  • Chapter 19: Learning from Examples
  • Chapter 20: Knowledge in Learning
  • Chapter 21: Learning Probabilistic Models
  • Chapter 22: Deep Learning
  • Chapter 23: Reinforcement Learning
  • Chapter 24: Natural Language Processing
  • Chapter 25: Deep Learning for Natural Language Processing
  • Chapter 26: Robotics
  • Chapter 27: Computer Vision
  • Chapter 28: Philosophy, Ethics, and Safety of AI
  • Chapter 29: The Future of AI

Need help?Get in touch