COS3751
Techniques of Artificial Intelligence

Artificial Intelligence: A Modern Approach

(4th edition)

by Stuart J. Russell and Peter Norvig

I. Artificial Intelligence

I.1. Introduction

I.1.1. What Is AI?

I.1.2. The Foundations of Artificial Intelligence

I.1.3. The History of Artificial Intelligence

I.1.4. The State of the Art

I.1.5. Risks and Benefits of AI

I.2. Intelligent Agents

I.2.1. Agents and Environments

I.2.2. Good Behavior: The Concept of Rationality

I.2.3. The Nature of Environments

I.2.4. The Structure of Agents

II. Problem-solving

II.3. Solving Problems by Searching

II.3.1. Problem-Solving Agents

II.3.2. Example Problems

II.3.3. Search Algorithms

II.3.4. Uninformed Search Strategies

II.3.5. Informed (Heuristic) Search Strategies

II.3.6. Heuristic Functions

II.4. Search in Complex Environments

II.4.1. Local Search and Optimization Problems

II.4.2. Local Search in Continuous Spaces

II.4.3. Search with Nondeterministic Actions

II.4.4. Search in Partially Observable Environments

II.4.5. Online Search Agents and Unknown Environments

II.5. Constraint Satisfaction Problems

II.5.1. Defining Constraint Satisfaction Problems

II.5.2. Constraint Propagation: Inference in CSPs

II.5.3. Backtracking Search for CSPs

II.5.4. Local Search for CSPs

II.5.5. The Structure of Problems

II.6. Adversarial Search and Games

II.6.1. Game Theory

II.6.2. Optimal Decisions in Games

II.6.3. Heuristic Alpha–Beta Tree Search

II.6.4. Monte Carlo Tree Search

II.6.5. Stochastic Games

II.6.6. Partially Observable Games

II.6.7. Limitations of Game Search Algorithms

III. Knowledge, reasoning, and planning

III.7. Logical Agents

III.7.1. Knowledge-Based Agents

III.7.2. The Wumpus World

III.7.4. Propositional Logic: A Very Simple Logic

III.7.5. Propositional Theorem Proving

III.7.6. Effective Propositional Model Checking

III.7.7. Agents Based on Propositional Logic

IV. Uncertain knowledge and reasoning

IV.12. Quantifying Uncertainty

IV.12.1. Acting under Uncertainty

IV.12.2. Basic Probability Notation

IV.12.3. Inference Using Full Joint Distributions

IV.12.4. Independence

IV.12.5. Bayes' Rule and Its Use

IV.12.6. Naive Bayes Models

IV.12.7. The Wumpus World Revisited

V. Machine Learning

V.19. Learning from Examples

V.19.1. Forms of Learning

V.19.2. Supervised Learning

V.19.3. Learning Decision Trees

V.19.4. Model Selection and Optimization

V.19.5. The Theory of Learning

V.19.6. Linear Regression and Classification

V.19.7. Nonparametric Models

V.19.8. Ensemble Learning

V.19.9. Developing Machine Learning Systems

VI. Communicating, perceiving, and acting

VI.24. Natural Language Processing

VI.24.1. Language Models

VI.24.2. Grammar

VI.24.3. Parsing

VI.24.4. Augmented Grammars

VI.24.5. Complications of Real Natural Language

VI.24.6. Natural Language Tasks

VII. Conclusions

VII.28. Philosophy, Ethics, and Safety of AI

VII.28.1. The Limits of AI

VII.28.2. Can Machines Really Think?

VII.28.3. The Ethics of AI

VII.29. The Future of AI

VII.29.1. AI Components

VII.29.2. AI Architectures