Xin Yao - Böcker

Evolvable hardware (EHW) is based on the idea of combining a reconfigurable hardware device with genetic algorithms to execute reconfiguration autonomously. FPGA (Field Programmable Gate Array) and PLD (Programmable Logic Devices) are typical examples of reconfigurable hardware devices, for which there is already a market worth more than USD2 Billion US dollars and growing at 23 per cent per year. An example of EHW is NASA's Space Technology 5 nanosatellites, which are scheduled to start measuring Earth's magnetosphere in late 2004. They were designed by NASA engineers using genetic algorithms and 32 Linux PCs. The computers generated small antenna-constructing programs (the genotypes) and executed them to produce designs (the phenotypes). If deployed it will be the first piece of evolved hardware ever to be launched into space.

Over the years, the use and application of evolutionary computation techniques has improved resulting in a set of computational intelligence (also known as modern heuristics) tools that are particularly adept for solving complex optimization problems. Moreover, they are characteristically more robust than traditional methods based on formal logics or mathematical programming for many real world OR/MS problems. Hence, evolutionary computation techniques have dealt with complex optimization problems better than traditional optimization techniques although they can be applied to easy and simple problems where conventional techniques work well. This volume reviews evolutionary computation techniques and surveys the most recent developments in their use for solving complex OR/MS problems.

Evolvable hardware (EHW) refers to hardware whose architecture/structure and functions change dynamically and autonomously in order to improve its performance in carrying out tasks. The emergence of this field has been profoundly influenced by the progress in reconfigurable hardware and evolutionary computation. Traditional hardware can be inflexible – the structure and its functions are often impossible to change once it is created. However, most real world problems are not fixed – they change with time. In order to deal with these problems efficiently and effectively, different hardware structures are necessary. EHW provides an ideal approach to make hardware "soft" by adapting the structure to a problem dynamically. The contributions in this book provide the basics of reconfigurable devices so that readers will be fully prepared to understand what EHW is, why it is necessary and how it is designed. The book also discusses the leading research in digital, analog and mechanical EHW.

Evolutionary computation techniques have attracted increasing att- tions in recent years for solving complex optimization problems. They are more robust than traditional methods based on formal logics or mathematical programming for many real world OR/MS problems. E- lutionary computation techniques can deal with complex optimization problems better than traditional optimization techniques. However, most papers on the application of evolutionary computation techniques to Operations Research /Management Science (OR/MS) problems have scattered around in different journals and conference proceedings. They also tend to focus on a very special and narrow topic. It is the right time that an archival book series publishes a special volume which - cludes critical reviews of the state-of-art of those evolutionary com- tation techniques which have been found particularly useful for OR/MS problems, and a collection of papers which represent the latest devel- ment in tackling various OR/MS problems by evolutionary computation techniques. This special volume of the book series on Evolutionary - timization aims at filling in this gap in the current literature. The special volume consists of invited papers written by leading - searchers in the field. All papers were peer reviewed by at least two recognised reviewers. The book covers the foundation as well as the practical side of evolutionary optimization.

Taking inspiration from self-awareness in humans, this book introduces the new notion of computational self-awareness as a fundamental concept for designing and operating computing systems. The basic ability of such self-aware computing systems is to collect information about their state and progress, learning and maintaining models containing knowledge that enables them to reason about their behaviour. Self-aware computing systems will have the ability to utilise this knowledge to effectively and autonomously adapt and explain their behaviour, in changing conditions.This book addresses these fundamental concepts from an engineering perspective, aiming at developing primitives for building systems and applications. It will be of value to researchers, professionals and graduate students in computer science and engineering.

Taking inspiration from self-awareness in humans, this book introduces the new notion of computational self-awareness as a fundamental concept for designing and operating computing systems.

The papers address all current issues in biologically inspired computing; they are organized in topical sections on theoretical and foundational issues, new algorithms, applications, multi-objective optimization, co-evolution, robotics and multi-agent systems, and learning classifier systems and data mining.

We are very pleased to present this LNCS volume, the proceedings of the 9th International Conference on Parallel Problem Solving from Nature (PPSN IX). PPSNisoneofthemostrespectedandhighlyregardedconferenceseriesinevo- tionary computation and natural computing / computation. This biennial event was ?rst held in Dortmund in 1990, and then in Brussels (1992), Jerusalem (1994), Berlin (1996), Amsterdam (1998), Paris (2000), Granada (2002), and Birmingham(2004).PPSNcontinuestobetheconferenceofchoicebyresearchers all over the world, who value its high quality. We received 255 paper submissions this year. After an extensive peer review process involving more than 1000 reviews, the programme committee selected the top 106 papers for inclusion in this volume and, of course, for presentation at the conference. This represents an acceptance rate of 42%. The papers included in this volume cover a wide range of topics, from e- lutionary computation to swarm intelligence and from bio-inspired computing to real-world applications. They represent some of the latest and best research in evolutionary and natural computation. Following the PPSN tradition, all - pers at PPSN IX were presented as posters. There were 7 sessions: each session consisting of around 15 papers. For each session, we covered as wide a range of topics as possible so that participants with di?erent interests could ?nd some relevant papers in every session.

This book constitutes the refereed proceedings of the 6th International Conference on Parallel Problem Solving from Nature, PPSN VI, held in Paris, France in September 2000. The 87 revised full papers presented together with two invited papers were carefully reviewed and selected from 168 submissions. The presentations are organized in topical sections on analysis and theory of evolutionary algorithms, genetic programming, scheduling, representations and operators, co-evolution, constraint handling techniques, noisy and non-stationary environments, combinatorial optimization, applications, machine learning and classifier systems, new algorithms and metaphors, and multiobjective optimization.

This volume contains the best carefully revised full papers selected from the presentations accepted for the AI '93 and AI '94 Workshop on Evolutionary Computation held in Australia.The 21 papers included cover a wide range of topics in the field of evolutionary computation, from constrained function optimization to combinatorial optimization, from evolutionary programming to genetic programming, from robotic strategy learning to co-evolutionary game strategy learning. The papers reflect important recent progress in the field; more than half of the papers come from overseas.

This book constitutes the thoroughly refereed post-conference documentation of the First Asia-Pacific Conference on Simulated Evolution and Learning, SEAL'96, held in Taejon, Korea, in November 1996.The 23 revised full papers were selected for inclusion in this book on the basis of 2 rounds of reviewing and improvements. Also included are invited papers by John L. Casti and Lawrence J. Fogel. The volume covers a wide range of current topics in simulated evolution and learning e.g. evolutionary optimization, evolutionary learning, artificial life, hybrid evolutionary fuzzy systems, evolutionary artificial neural networks, co-evolution, novel evolutionary approaches to computer tomography image reconstruction, power systems load flow control, and water flow control in cropped soils.

This book constitutes the refereed post-workshop proceedings of the Second Asia-Pacific Conference on Simulated Evolution and Learning, SEAL '98, held in Canberra, Australia in November 1998. The 59 revised papers presented were carefully selected during two rounds of reviewing from a total of initially 92 submissions. The book covers a wide range of topics in simulated evolution and learning, from self-adaption to dynamic modelling, from reinforcement learning to agent systems, from evolutionary games to evolutionary economics, from theoretical results to successful applications, etc.

This book constitutes the refereed proceedings of the 8th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2007, held in Birmingham, UK, in December 2007. The papers include topical sections on learning and information processing, data mining and information management, bioinformatics and neuroinformatics, agents and distributed systems, financial engineering and modeling, and agent-based approach to service sciences.

This book provides a compilation on the state-of-the-art and recent advances of evolutionary computation for dynamic optimization problems. The motivation for this book arises from the fact that many real-world optimization problems and engineering systems are subject to dynamic environments, where changes occur over time. Key issues for addressing dynamic optimization problems in evolutionary computation, including fundamentals, algorithm design, theoretical analysis, and real-world applications, are presented. "Evolutionary Computation for Dynamic Optimization Problems" is a valuable reference to scientists, researchers, professionals and students in the field of engineering and science, particularly in the areas of computational intelligence, nature- and bio-inspired computing, and evolutionary computation.

This book constitutes the refereed proceedings of the 14th International Conference on Intelligent Data Engineering and Automated Learning, IDEAL 2013, held in Hefei, China, in October 2013. The 76 revised full papers presented were carefully reviewed and selected from more than 130 submissions. These papers provided a valuable collection of latest research outcomes in data engineering and automated learning, from methodologies, frameworks and techniques to applications. In addition to various topics such as evolutionary algorithms, neural networks, probabilistic modelling, swarm intelligent, multi-objective optimisation, and practical applications in regression, classification, clustering, biological data processing, text processing, video analysis, including a number of special sessions on emerging topics such as adaptation and learning multi-agent systems, big data, swarm intelligence and data mining, and combining learning and optimisation in intelligent data engineering.

This book provides a compilation on the state-of-the-art and recent advances of evolutionary computation for dynamic optimization problems. The motivation for this book arises from the fact that many real-world optimization problems and engineering systems are subject to dynamic environments, where changes occur over time. Key issues for addressing dynamic optimization problems in evolutionary computation, including fundamentals, algorithm design, theoretical analysis, and real-world applications, are presented. "Evolutionary Computation for Dynamic Optimization Problems" is a valuable reference to scientists, researchers, professionals and students in the field of engineering and science, particularly in the areas of computational intelligence, nature- and bio-inspired computing, and evolutionary computation.

Evolutionary computation is the study of computational systems which use ideas and get inspiration from natural evolution and adaptation. This book is devoted to the theory and application of evolutionary computation. It is a self-contained volume which covers both introductory material and selected advanced topics. The book can roughly be divided into two major parts: the introductory one and the one on selected advanced topics. Each part consists of several chapters which present an in-depth discussion of selected topics. A strong connection is established between evolutionary algorithms and traditional search algorithms. This connection enables us to incorporate ideas in more established fields into evolutionary algorithms. The book is aimed at a wide range of readers. It does not require previous exposure to the field since introductory material is included. It will be of interest to anyone who is interested in adaptive optimization and learning. People in computer science, artificial intelligence, operations research, and various engineering fields will find it particularly interesting.

AI '95 is the Eighth Australian Joint Conference on Artificial Intelligence. The main theme of AI '95 is "bridging the gaps", i.e., bridging the gap between the classical symbolic approach and other subsymbolic approaches, such as artificial neural networks, evolutionary computation and artificial life, to AI and bridging the gap between the AI theory and real world applications. The invited keynote speakers and accepted papers reflect our main theme.This volume includes 66 full-length papers accepted for oral presentation and 30 one-page summaries of the papers accepted for poster presentation. The titles of presented papers in the special sessions on real-world applications are also included. These papers cover a wide range of topics related to AI, such as automated reasoning, knowledge representation, knowledge acquisition, machine learning, evolutionary computation, neural networks, robotics, expert systems, multi-agent systems, fuzzy logic systems, natural language processing, pattern recognition, distributed AI, etc. A good proportion of the papers describe AI applications.AI '95 features three international keynote speakers. Professor Kenneth De Jong from George Mason University is an authority in evolutionary computation. He will discuss evolving intelligence in his keynote speech. Professor William Clancey from the Institute for Research on Learning is a well respected celebrity in AI. He will explore the relationship between symbolic and subsymbolic reasoning in his keynote speech. Both Professor De Jong's and Professor Clancey's papers are included in this volume. The third keynote speaker is Dr Suan Garavaglia of Dun and Bradstreet, a well-known in the financial world for her work relating to the use of AI in finance.

Inspired by the Darwinian framework of evolution through natural selection and adaptation, the field of evolutionary computation has been growing very rapidly, and is today involved in many diverse application areas. This book covers the latest advances in the theories, algorithms, and applications of simulated evolution and learning techniques. It provides insights into different evolutionary computation techniques and their applications in domains such as scheduling, control and power, robotics, signal processing, and bioinformatics. The book will be of significant value to all postgraduates, research scientists and practitioners dealing with evolutionary computation or complex real-world problems.This book has been selected for coverage in:• Index to Scientific & Technical Proceedings (ISTP CDROM version / ISI Proceedings)• CC Proceedings — Engineering & Physical Sciences

In 1984, Robert Axelrod published a book, relating the story of two competitions which he ran, where invited academics entered strategies for the Iterated Prisoners' Dilemma. The book, almost 20 years on, is still widely read and cited by academics and the general public.As a celebration of that landmark work, we have recreated those competitions to celebrate its 20th anniversary, by again inviting academics to submit prisoners' dilemma strategies. The first of these new competitions was run in July 2004, and the second in April 2005. Iterated Prisoners' Dilemma: 20 Years On essentially provides an update of the Axelrod's book.Specifically, it