本书为广大学生和人工智能开发人员提供了学习人工智能相关概念的一种新思路。

书中包含人工智能在多个领域的许多最新应用，这些领域包括游戏程序设计、群体智能、智能Agent、神经网络、人工免疫系统、遗传算法、模式识别、数值优化以及数据挖掘等。本书还讨论了从早期的LISP语言到近期的Python语言等多种人工智能语言。书中不仅包括了人工智能的理论和主要课题，还介绍了从数据输入到转换再到数据输出（即算法的使用）的实际需要的信息。因为传统的人工智能概念目前仅仅表示算法的各种类型，因此需要用一种不同的方法来介绍人工智能算法。这种“传感器－算法－效应器”的方法为这些算法提供了一个基础环境，能够帮助学生和人工智能从业者更好地理解它们，从而更好地应用这些算法。

本书包含当前人工智能（AI）研究的主要内容，尤其强调实际应用，涉及数据挖掘等许多最新应用领域。全书共13章，分别讲述了AI的历史、不用知识的搜索、用知识的搜索、AI与博弈、知识表示、机器学习、演化计算、神经网络I、机器人学与AI、智能Agent、来自生物的模型与混合模型以及AⅡ语言。本书给出了算法的较详细实现，与现有的以理论基础为核心的大多数经典人工智能著作相比，本书有自身的鲜明特色，且内容与国内人工智能课程的教学内容吻合，尤其有利于培养学生解决人工智能实际问题的能力。

本书适合高等学校计算机、自动化等信息学科的本科生和研究生阅读，也适合广大人工智能爱好者自学使用，本书也能为人工智能研究人员了解各种算法的设计思路和具体实现框架提供参考。

Chapter 1 The History of AI

　What is Intelligence?

　The Search for Mechanical Intelligence

　The Very Early Days(the early 1950s)

　Artificial Intelligence Emerges as a Field

　AI's Winter

　AI Re-emerges

　AI Inter-Disciplinary R&D

　Systems Approach

　Overview of this Book

　Chapter Summary

　References

　Resources

　Exercises

Chapter 2 Uninformed Search

　Search and AI

　Classes of Search

　General State Space Search

　Trees, Graphs, and Representation

　Uninformed Search

　Improvements

　Algorithm Advantages

　Chapter Summary

　Algorithms Summary

　References

　Exercises

Chapter 3 Informed Search

　Informed Search

　Best-First Search(Best-FS)

　A* Search

　Hill-Climbing Search

　Simulated Annealing(SA)

　Tabu Search

　Constraint Satisfaction Problems(CSP)

　Constraint Satisfaction Algorithms

　Chapter Summary

　Algorithms Summary

　References

　Resources

　Exercises

Chapter 4 AI and Games

　Two-Player Games

　The Minimax Algorithm

　Classical Game AI

　Video Game AI

　Chapter Summary

　References

　Resources

　Exercises

Chapter 5 Knowledge Representation

　Introduction

　Types of Knowledge

　The Role of Knowledge

　Semantic Networks

　Frames

　Propositional Logic

　First-Order Logic(Predicate Logic)

　Semantic Web

　Computational Knowledge Discovery

　Ontology

　Communication of Knowledge

　Chapter Summary

　References

　Resources

　Exercises

Chapter 6 Machine Learning

　Machine-Learning Algorithms

　Chapter Summary

　Resources

　Exercises

Chapter 7 Evolutionary Computation

 Short History of Evolutionary Computation

　Biological Motivation

 Genetic Algorithms (GA)

 Genetic Programming (GP)

 Evolutionary Strategies (ES)

 Differential Evolution (DE)

 Particle Swarm Optimization (PSO)

 Evolvable Hardware

 Chapter Summary

 References

 Resources

 Exercises

Chapter 8 Neural Networks I

 Short History of Neural Networks

 Biological Motivation

 Fundamentals of Neural Networks

 The Perceptron

 Least-Mean-Square (LMS) Learning

 Learning with Backpropagation

 Probabilistic Neural Networks (PNN)

 Other Neural Network Architectures

 Tips for Building Neural Networks

 Chapter Summary

 References

 Exercises

Chapter 9 Neural Networks II

 Unsupervised Learning

 Hebbian Learning

 Simple Competitive Learning

 K-Means Clustering

 Adaptive Resonance Theory (ART)

 Hopfield Auto-Associative Model

 Chapter Summary

 References

 Exercises

Chapter 10 Robotics and AI

 Introduction to Robotics

 Braitenburg Vehicles

 Natural Sensing and Control

 Perception with Sensors

 Actuation with Effectors

 Robotic Control Systems

 Simple Control Architectures

 Movement Planning

 Group or Distributed Robotics

 Robot Programming Languages

 Robot Simulators

 Chapter Summary

 References

 Resources

 Exercises

Chapter 11 Intelligent Agents

 Anatomy of an Agent

 Agent Properties and AI

 Agent Environments

 Agent Taxonomies

 Agent Architectures

 Agent Languages

 Agent Communication

 ACL (FIPA Agent Communication Language)

 Chapter Summary

 Resources

 References

 Exercises

Chapter 12 Biologically Inspired and Hybrid Models

 Cellular Automata (CA)

 Artificial Immune Systems

 Artificial Life

 Fuzzy Systems

 Evolutionary Neural Networks

 Ant Colony Optimization (ACO)

 Affective Computing

 Resources

Chapter 13 The Languages of AI

 Language Taxonomy

 Languages of AI

 Other Languages

 Chapter Summary

 References

 Resources

 Exercises