Artificial Intelligence: A Modern Approach, 4/e (美國原版)
內容描述
The most comprehensive, up-to-date introduction to the theory and practice of artificial intelligence
The long-anticipated revision of Artificial Intelligence: A Modern Approach explores the full breadth and depth of the field of artificial intelligence (AI). The 4th Edition brings readers up to date on the latest technologies, presents concepts in a more unified manner, and offers new or expanded coverage of machine learning, deep learning, transfer learning, multiagent systems, robotics, natural language processing, causality, probabilistic programming, privacy, fairness, and safe AI.
Features
Offer the most comprehensive, up-to-date introduction to the theory and practice of artificial intelligence
Nontechnical learning material introduces major concepts using intuitive explanations, before going into mathematical or algorithmic details. The nontechnical language makes the book accessible to a broader range of readers.
A unified approach to AI shows students how the various subfields of AI fit together to build actual, useful programs.
UPDATED - The basic definition of AI systems is generalized to eliminate the standard assumption that the objective is fixed and known by the intelligent agent; instead, the agent may be uncertain about the true objectives of the human(s) on whose behalf it operates.
In-depth coverage of both basic and advanced topics provides students with a basic understanding of the frontiers of AI without compromising complexity and depth.
The Author-Maintained Website at http://aima.cs.berkeley.edu/ includes text-related comments and discussions, exercises, an online code repository, Instructor Resources, and more!
UPDATED - Interactive student exercises are now featured on the website to allow for continuous updating and additions.
UPDATED - Online software gives students more opportunities to complete projects, including implementations of the algorithms in the book, plus supplemental coding examples and applications in Python, Java, and Javascript.
NEW - Instructional video tutorials deepen students’ engagement and bring key concepts to life.
A flexible format makes the text adaptable for varying instructors' preferences.
Stay current with the latest technologies and present concepts in a more unified manner
NEW - New chapters feature expanded coverage of probabilistic programming (Ch. 15); multiagent decision making (Ch. 18 with Michael Wooldridge); deep learning (Ch. 21 with Ian Goodfellow); and deep learning for natural language processing (Ch. 24 with Jacob Devlin and Mei-Wing Chang).
UPDATED - Increased coverage of machine learning.
UPDATED - Significantly updated material on robotics includes robots that interact with humans and the application of reinforcement learning to robotics.
NEW - New section on causality by Judea Pearl.
NEW - New sections on Monte Carlo search for games and robotics.
NEW - New sections on transfer learning for deep learning in general and for natural language.
NEW - New sections on privacy, fairness, the future of work, and safe AI.
NEW - Extensive coverage of recent advances in AI applications.
UPDATED - Revised coverage of computer vision, natural language understanding, and speech recognition reflect the impact of deep learning methods on these fields.
New to This Edition
Offer the most comprehensive, up-to-date introduction to the theory and practice of artificial intelligence
The basic definition of AI systems is generalized to eliminate the standard assumption that the objective is fixed and known by the intelligent agent; instead, the agent may be uncertain about the true objectives of the human(s) on whose behalf it operates.
The Author-Maintained Website at http://aima.cs.berkeley.edu/ includes text-related comments and discussions, exercises, an online code repository, Instructor Resources, and more!
Interactive student exercises are now featured on the website to allow for continuous updating and additions.
Updated online software gives students more opportunities to complete projects, including implementations of the algorithms in the book, plus supplemental coding examples and applications in Python, Java, and Javascript.
New instructional video tutorials deepen students’ engagement and bring key concepts to life.
Stay current with the latest technologies and present concepts in a more unified manner
New chapters feature expanded coverage of probabilistic programming (Ch. 15); multiagent decision making (Ch. 18 with Michael Wooldridge); deep learning (Ch. 21 with Ian Goodfellow); and deep learning for natural language processing (Ch. 24 with Jacob Devlin and Mei-Wing Chang).
Increased coverage of machine learning.
Significantly updated material on robotics includes robots that interact with humans and the application of reinforcement learning to robotics.
New section on causality by Judea Pearl.
New sections on Monte Carlo search for games and robotics.
New sections on transfer learning for deep learning in general and for natural language.
New sections on privacy, fairness, the future of work, and safe AI.
Extensive coverage of recent advances in AI applications.
Revised coverage of computer vision, natural language understanding, and speech recognition reflect the impact of deep learning methods on these fields.
目錄大綱
Part I: Artificial Intelligence
- Introduction
1.1 What Is AI?
1.2 The Foundations of Artificial Intelligence
1.3 The History of Artificial Intelligence
1.4 The State of the Art
1.5 Risks and Benefits of AI - Intelligent Agents
2.1 Agents and Environments
2.2 Good Behavior: The Concept of Rationality
2.3 The Nature of Environments
2.4 The Structure of Agents
Part II: Problem Solving - Solving Problems by Searching
3.1 Problem-Solving Agents
3.2 Example Problems
3.3 Search Algorithms
3.4 Uninformed Search Strategies
3.5 Informed (Heuristic) Search Strategies
3.6 Heuristic Functions - Search in Complex Environments
4.1 Local Search and Optimization Problems
4.2 Local Search in Continuous Spaces
4.3 Search with Nondeterministic Actions
4.4 Search in Partially Observable Environments
4.5 Online Search Agents and Unknown Environments - Adversarial Search and Games
5.1 Game Theory
5.2 Optimal Decisions in Games
5.3 Heuristic Alpha--Beta Tree Search
5.4 Monte Carlo Tree Search
5.5 Stochastic Games
5.6 Partially Observable Games
5.7 Limitations of Game Search Algorithms - Constraint Satisfaction Problems
6.1 Defining Constraint Satisfaction Problems
6.2 Constraint Propagation: Inference in CSPs
6.3 Backtracking Search for CSPs
6.4 Local Search for CSPs
6.5 The Structure of Problems
Part III: Knowledge and Reasoning - Logical Agents
7.1 Knowledge-Based Agents
7.2 The Wumpus World
7.3 Logic
7.4 Propositional Logic: A Very Simple Logic
7.5 Propositional Theorem Proving
7.6 Effective Propositional Model Checking
7.7 Agents Based on Propositional Logic - First-Order Logic
8.1 Representation Revisited
8.2 Syntax and Semantics of First-Order Logic
8.3 Using First-Order Logic
8.4 Knowledge Engineering in First-Order Logic - Inference in First-Order Logic
9.1 Propositional vs.~First-Order Inference
9.2 Unification and First-Order Inference
9.3 Forward Chaining
9.4 Backward Chaining
9.5 Resolution - Knowledge Representation
10.1 Ontological Engineering
10.2 Categories and Objects
10.3 Events
10.4 Mental Objects and Modal Logic
10.5 Reasoning Systems for Categories
10.6 Reasoning with Default Information - Automated Planning
11.1 Definition of Classical Planning
11.2 Algorithms for Classical Planning
11.3 Heuristics for Planning
11.4 Hierarchical Planning
11.5 Planning and Acting in Nondeterministic Domains
11.6 Time, Schedules, and Resources
11.7 Analysis of Planning Approaches - Quantifying Uncertainty
12.1 Acting under Uncertainty
12.2 Basic Probability Notation
12.3 Inference Using Full Joint Distributions
12.4 Independence
12.5 Bayes' Rule and Its Use
12.6 Naive Bayes Models
12.7 The Wumpus World Revisited
Part IV: Uncertain Knowledge and Reasoning - Probabilistic Reasoning
13.1 Representing Knowledge in an Uncertain Domain
13.2 The Semantics of Bayesian Networks
13.3 Exact Inference in Bayesian Networks
13.4 Approximate Inference for Bayesian Networks
13.5 Causal Networks - Probabilistic Reasoning over Time
14.1 Time and Uncertainty
14.2 Inference in Temporal Models
14.3 Hidden Markov Models
14.4 Kalman Filters
14.5 Dynamic Bayesian Networks - Probabilistic Programming
15.1 Relational Probability Models
15.2 Open-Universe Probability Models
15.3 Keeping Track of a Complex World
15.4 Programs as Probability Models - Making Simple Decisions
16.1 Combining Beliefs and Desires under Uncertainty
16.2 The Basis of Utility Theory
16.3 Utility Functions
16.4 Multiattribute Utility Functions
16.5 Decision Networks
16.6 The Value of Information
16.7 Unknown Preferences - Making Complex Decisions
17.1 Sequential Decision Problems
17.2 Algorithms for MDPs
17.3 Bandit Problems
17.4 Partially Observable MDPs
17.5 Algorithms for solving POMDPs
Part V: Learning - Multiagent Decision Making
18.1 Properties of Multiagent Environments
18.2 Non-Cooperative Game Theory
18.3 Cooperative Game Theory
18.4 Making Collective Decisions - Learning from Examples
19.1 Forms of Learning
19.2 Supervised Learning
19.3 Learning Decision Trees
19.4 Model Selection and Optimization
19.5 The Theory of Learning
19.6 Linear Regression and Classification
19.7 Nonparametric Models
19.8 Ensemble Learning
19.9 Developing Machine Learning Systems - Learning Probabilistic Models
20.1 Statistical Learning
20.2 Learning with Complete Data
20.3 Learning with Hidden Variables: The EM Algorithm - Deep Learning
21.1 Simple Feedforward Networks
21.2 Mixing and matching models, loss functions and optimizers
21.3 Loss functions
21.4 Models
21.5 Optimization Algorithms
21.6 Generalization
21.7 Recurrent neural networks
21.8 Unsupervised, semi-supervised and transfer learning
21.9 Applications
Part VI: Communicating, Perceiving, and Acting - Reinforcement Learning
22.1 Learning from Rewards
22.2 Passive Reinforcement Learning
22.3 Active Reinforcement Learning
22.4 Safe Exploration
22.5 Generalization in Reinforcement Learning
22.6 Policy Search
22.7 Applications of Reinforcement Learning - Natural Language Processing
23.1 Language Models
23.2 Grammar
23.3 Parsing
23.4 Augmented Grammars
23.5 Complications of Real Natural Language
23.6 Natural Language Tasks - Deep Learning for Natural Language Processing
24.1 Limitations of Feature-Based NLP Models
24.2 Word Embeddings
24.3 Recurrent Neural Networks
24.4 Sequence-to-sequence Models
24.5 The Transformer Architecture
24.6 Pretraining and Transfer Learning
24.7 Introduction
24.8 Image Formation
24.9 Simple Image Features
24.10 Classifying Images
24.11 Detecting Objects
24.12 The 3D World
24.13 Using Computer Vision - Robotics
25.1 Robots
25.2 Robot Hardware
25.3 What kind of problem is robotics solving?
25.4 Robotic Perception
25.5 Planning and Control
25.6 Planning Uncertain Movements
25.7 Reinforcement Learning in Robotics
25.8 Humans and Robots
25.9 Alternative Robotic Frameworks
25.10 Application Domains
Part VII: Conclusions - Philosophy and Ethics of AI
26.1 Weak AI: What are the Limits of AI?
26.2 Strong AI: Can Machines Really Think?
26.3 The Ethics of AI - The Future of AI
27.1 AI Components
27.2 AI Architectures
Appendix A: Mathematical Background
A.1 Complexity Analysis and O() Notation
A.2 Vectors, Matrices, and Linear Algebra
A.3 Probability Distributions
Appendix B: Notes on Languages and Algorithms
B.1 Defining Languages with Backus--Naur Form (BNF)
B.2 Describing Algorithms with Pseudocode
B.3 Online Supplemental Material
作者介紹
Stuart Russell was born in 1962 in Portsmouth, England. He received his B.A. with first-class honours in physics from Oxford University in 1982, and his Ph.D. in computer science from Stanford in 1986. He then joined the faculty of the University of California at Berkeley, where he is a professor and former chair of computer science, director of the Center for Human-Compatible AI, and holder of the Smith–Zadeh Chair in Engineering. In 1990, he received the Presidential Young Investigator Award of the National Science Foundation, and in 1995 he was co-winner of the Computers and Thought Award. He is a Fellow of the American Association for Artificial Intelligence, the Association for Computing Machinery, and the American Association for the Advancement of Science, and Honorary Fellow of Wadham College, Oxford, and an Andrew Carnegie Fellow. He held the Chaire Blaise Pascal in Paris from 2012 to 2014. He has published over 300 papers on a wide range of topics in artificial intelligence. His other books include: The Use of Knowledge in Analogy and Induction, Do the Right Thing: Studies in Limited Rationality (with Eric Wefald), and Human Compatible: Artificial Intelligence and the Problem of Control.
Peter Norvig is currently Director of Research at Google, Inc., and was the director responsible for the core Web search algorithms from 2002 to 2005. He is a Fellow of the American Association for Artificial Intelligence and the Association for Computing Machinery. Previously, he was head of the Computational Sciences Division at NASA Ames Research Center, where he oversaw NASA’s research and development in artificial intelligence and robotics, and chief scientist at Junglee, where he helped develop one of the first Internet information extraction services. He received a B.S. in applied mathematics from Brown University and a Ph.D. in computer science from the University of California at Berkeley. He received the Distinguished Alumni and Engineering Innovation awards from Berkeley and the Exceptional Achievement Medal from NASA. He has been a professor at the University of Southern California and a research faculty member at Berkeley. His other books are: Paradigms of AI Programming: Case Studies in Common Lisp, Verbmobil: A Translation System for Face-to-Face Dialog, and Intelligent Help Systems for UNIX.
The two authors shared the inaugural AAAI/EAAI Outstanding Educator award in 2016.
_@9787111492115_https://static.coderbridge.com/images/books/9787111492115.jpg)