群体智能James Kennedy,Russell C Eberhart,Yuhui Shi作者简介、书籍目录、内容摘要、编辑推荐
群体智能是通过模拟自然界生物群体行为来实现人工智能的一种方法。本书综合运用认知科学、社会心理学、人工智能和演化计算等学科知识,提供了一些非常有价值的新见解,并将这些见解加以应用,以解决困难的工程问题。书中首先探讨了基础理论,然后详尽展示如何将这些理论和模型应用于新的计算智能方法(粒子群)中,以适应智能系统的行为,最后描述了应用粒子群优化算法的好处,提供了强有力的优化、学习和问题解决的方法。 本书主要面向计算机相关学科的高年级本科生或研究生以及相关领域的研究与开发技术人员。
作者简介
James Kennedy社会心理学家。自1994年起,他一直致力于粒子群算法的研究工作,并与Russell C.Eberhart共同开发了粒子群优化算法。目前在美国劳工部从事调查方法的研究工作。他在计算机科学和社会科学杂志和学报上发表过许多关于粒子群的论文。
RusselI C.Eberhart 普度大学电子与计算机工程系主任。IEEE会士。与JamesKennedy共同提出了粒子群优化算法。曾任IEEE神经网络委员会的主席。除了本书之外,他还著有《计算智能:从概念到实现》(影印版由人民邮电出版社出版)等。
Yuhui Shi (史玉回)国际计算智能领域专家,现任Joumal ofSwarm Intellgence编委,IEEE CIS群体智能任务组主席,西交利物浦大学电子与电气工程系教授。1992年获东南大学博士学位,先后在美国、韩国、澳大利亚等地从事研究工作,曾任美国电子资讯系统公司专家长达9年。他还是《计算智能:从概念到实现》一书的作者之一。
书籍目录
part one Foundations chapter one Models and Concepts of Life and Intelligence
The Mechanics of Life and Thought
Stochastic Adaptation: Is Anything Ever Really Random?
The “Two Great Stochastic Systems”
The Game of Life: Emergence in Complex Systems
The Game of Life
Emergence
Cellular Automata and the Edge of Chaos
Artificial Life in Computer Programs
Intelligence: Good Minds in People and Machines
Intelligence in People: The Boring Criterion
Intelligence in Machines: The Turing Criterion
chapter two Symbols, Connections, and Optimization by Trial and Error
Symbols in Trees and Networks
Problem Solving and Optimization
A Super-Simple Optimization Problem
Three Spaces of Optimization
Fitness Landscapes
High-Dimensional Cognitive Space and Word Meanings
Two Factors of Complexity: NK Landscapes
Combinatorial Optimization
Binary Optimization
Random and Greedy Searches
Hill Climbing
Simulated Annealing
Binary and Gray Coding
Step Sizes and Granularity
Optimizing with Real Numbers
Summary
chapter three On Our Nonexistence as Entities: The Social Organism
Views of Evolution
Gaia: The Living Earth
Differential Selection
Our Microscopic Masters?
Looking for the Right Zoom Angle
Flocks, Herds, Schools, and Swarms: Social Behavior as Optimization
Accomplishments of the Social Insects
Optimizing with Simulated Ants: Computational Swarm Intelligence
Staying Together but Not Colliding: Flocks, Herds, and Schools
Robot Societies
Shallow Understanding
Agency
Summary
chapter four Evolutionary Computation Theory and Paradigms
Introduction
Evolutionary Computation History
The Four Areas of Evolutionary Computation
Genetic Algorithms
Evolutionary Programming
Evolution Strategies
Genetic Programming
Toward Unification
Evolutionary Computation Overview
EC Paradigm Attributes
Implementation
Genetic Algorithms
An Overview
A Simple GA Example Problem
A Review of GA Operations
Schemata and the Schema Theorem
Final Comments on Genetic Algorithms
Evolutionary Programming
The Evolutionary Programming Procedure
Finite State Machine Evolution
Function Optimization
Final Comments
Evolution Strategies
Mutation
Recombination
Selection
Genetic Programming
Summary
chapter five Humans—Actual, Imagined, and Implied
chapter six Thinking Is Socialpart two The Particle Swarm and Collective Intelligence chapter seven The Particle Swarm
chapter eight Variations and Comparisons
chapter nine Applications
chapter ten Implications and Speculationschapter eleven And in Conclusion Appendix A Statistics for Swarmers Appendix B Genetic Algorithm Implementation Glossary References Index
章节摘录
插图:
媒体关注与评论
“本书内容丰富,富于启发性和思想性,强烈推荐给所有的演进计算研究人员。”
——Genetic Programming and EvolvableMachines
“这本书极为出色,不愧为PSO和群体智能的最佳参考书:”
——Konstantions E.Parsopoulos 希腊Palras大学
编辑推荐
《群体智能》由粒子群优化算法之父撰写,是该领域毋庸置疑的经典著作。作者提出,人类智能来源于社会环境中个体之间的交互,这种智能模型可以有效地应用到人工智能系统中去。书中首先从社会心理学、认知科学和演化计算等多个角度阐述了这种新方法的基础,然后详细说明了应用这些理论和模型所得出的新的计算智能方法——粒子群优化,进而深入地探讨了如何将粒子群优化应用于广泛的工程问题。群体智能是近年来发展迅速的人工智能学科领域。通过研究分散、自组织的动物群体和人类社会的智能行为,学者们提出了许多迥异于传统思路的智能算法,很好地解决了不少原来非常棘手的复杂工程问题。与蚁群算法齐名的粒子群优化(particle swarm optimizatiotl,简称PSO)算法就是其中最受瞩目、应用最为广泛的成果之一。《群体智能》的C及ViSLlaI Basic源代码可以在图灵网站《群体智能》网页免费注册下载。