Bücher der Reihe Lecture Notes in Artificial Intelligence

The Advanced Course on Artificial Intelligence ACAI 2001 with the subtitle M ulti- Agent Systems and Their Applications , held in Prague, Czech Republic, was a joint event of ECCAI (the European Coordinating Committee for Artificial Intelligence) and AgentLink, the European Network of Excellence for Agent-Based Computing. Whereas ECCAI organizes two-week ACAI courses on different topics every second year, AgentLink s European Agent Systems Summer School (EASSS) has been an annual event since 1999. This year, both of these important events were merged together, giving weight to the fact that multi-agent systems currently represent one of the hottest topics in AI research. The name, ACAI 2001 Summer School, is intended to emphasize that this event continues the tradition of regular ECCAI activities (ACAI), as well as the EASSS summer schools of AgentLink. The Prague ACAI Summer School was proposed and initiated by both the Gerstner Laboratory, Czech Technical University, Prague (GL-CTU) and the Czech Society for Cybernetics and Informatics (CSKI), with the support of the Austrian Research Institute for Artificial Intelligence in Vienna (OFAI). Part of our motivation was catalyzed by experience gained in 1992 during the International Summer School Advanced Topics in Artificial Intelligence (see Springer s LNAI vol. 617) which was organized by the same Czech and Austrian bodies. One of the most important stimulating factors behind the organization of ACAI 2001 was the support provided by the European Commission to the Gerstner Laboratory within the frame of the MIRACLE Center of Excellence project (IST No.

Building research grade multi-agent systems usually involves a broad variety of software infrastructure ingredients like planning, scheduling, coordination, communication, transport, simulation, and module integration technologies and as such constitutes a great challenge to the individual researcher active in the area.The book presents a collection of papers on approaches that will help make deployed and large scale multi-agent systems a reality. The first part focuses on available infrastructure and requirements for constructing research-grade agents and multi-agent systems. The second part deals with support in infrastructure and software development methods for multi-agent systems that can directly support coordination and management of large multi-agent communities; performance analysis and scalability techniques are needed to promote deployment of multi-agent systems to professionals in software engineering and information technology.

It is generally understood that the present approachs to computing do not have the performance, flexibility, and reliability of biological information processing systems. Although there is a comprehensive body of knowledge regarding how information processing occurs in the brain and central nervous system this has had little impact on mainstream computing so far. This book presents a broad spectrum of current research into biologically inspired computational systems and thus contributes towards developing new computational approaches based on neuroscience. The 39 revised full papers by leading researchers were carefully selected and reviewed for inclusion in this anthology. Besides an introductory overview by the volume editors, the book offers topical parts on modular organization and robustness, timing and synchronization, and learning and memory storage.

This volume contains the contributions to the Joint German/Austrian Con- rence on Arti?cial Intelligence, KI 2001, which comprises the 24th German and the 9th Austrian Conference on Arti?cial Intelligence. They are divided into the following categories: - 2 contributions by invited speakers of the conference; - 29 accepted technical papers, of which 5 where submitted as application papers and 24 as papers on foundations of AI; - 4 contributions by participants of the industrial day, during which companies working in the ?eld presented their AI applications. After a long period of separate meetings, the German and Austrian Societies * for Arti?cial Intelligence, KI and OGAI, decided to hold a joint conference in Vienna in 2001. The two societies had previously held one joint conference. This took place in Ottstein, a small town in Lower Austria, in 1986. At that time, the rise of expert system technology had also renewed interest in AI in general, with quite some expectations for future advances regarding the use of AI techniques in applications pervading many areas of our daily life. Since then ?fteen years have passed, and we may want to comment, at the beginning of a newcentury, on the progress that has been made in this direction.

This book constitutes the refereed proceedings of the scientific track of the 7th Congress of the Italian Association for Artificial Intelligence, AI*IA 2001, held in Bari, Italy, in September 2001.The 25 revised long papers and 16 revised short papers were carefully reviewed and selected for inclusion in the volume. The papers are organized in topical sections on machine learning; automated reasoning; knowledge representation; multi-agent systems; natural language processing; perception, vision, and robotics; and planning and scheduling.

These are the proceedings of the Fifth International Workshop on Cooperative Information Agents, held in Modena, Italy, September 6-8, 2001. Information agent technology has become one of the major key technologies for the Internet and the World Wide Web. It mainly emerged as a response to the challenges of cyberspace from both the technological and human user perspective. Development of information agents requires expertise from di?erent research disciplines such as Arti?cial Intelligence (AI), advanced databases and knowledge base systems, distributed information systems, information retrieval, and Human Computer Interaction (HCI). The ?fth international workshop on Cooperative Information Agents (CIA) continued the tradition by capturing the intrinsic interdisciplinary nature of the above research area by calling for contributions from di?erent research communities, and by promoting open and informative discussions on all related topics. In keeping with tradition, the workshop featured a sequence of regular and invited talks of excellence given by leading experts in the ?eld. This year the topics of the talks are mainly on the challenges of information agents in the upcoming age of ubiquitous and pervasive computing. These challenges are in particular due to the necessity of an e?cient utilization, evolution, and trust management of information agents for user-oriented information search, pro- sion, and visualization in networked computing environments with small, mobile, and embedded devices. A di?erent issue concerns the potential of agent-based support of massive distributed data warehousing worldwide.

Why is the question of the di?erence between living and non-living matter - tellectually so attractive to the man of the West? Where are our dreams about our own ability to understand this di?erence and to overcome it using the ?rmly established technologies rooted? Where are, for instance, the cultural roots of the enterprises covered nowadays by the discipline of Arti?cial Life? Cont- plating such questions, one of us has recognized [6] the existence of the eternal dream of the man of the West expressed, for example, in the Old Testament as follows: . . . the Lord God formed the man from the dust of the ground and breathed into his nostrils the breath of life, and the man became a living being (Genesis, 2. 7). This is the dream about the workmanlike act of the creation of Adam from clay, about the creation of life from something non-living, and the con?dence in the magic power of technologies. How has this dream developed and been converted into a reality, and how does it determine our present-day activities in science and technology? What is this con?dence rooted in? Then God said: "e;Let us make man in our image. . . "e; (Genesis, 1. 26). Man believes in his own ability to repeat the Creator's acts, to change ideas into real things, because he believes he is godlike. This con?dence is - using the trendy Dawkins' term - perhaps the most important cultural meme of the West.

This book constitutes the refereed proceedings of the 12th European Conference on Machine Learning, ECML 2001, held in Freiburg, Germany, in September 2001.The 50 revised full papers presented together with four invited contributions were carefully reviewed and selected from a total of 140 submissions. Among the topics covered are classifier systems, naive-Bayes classification, rule learning, decision tree-based classification, Web mining, equation discovery, inductive logic programming, text categorization, agent learning, backpropagation, reinforcement learning, sequence prediction, sequential decisions, classification learning, sampling, and semi-supervised learning.

The biennial Brazilian Symposium on Arti?cial Intelligence (SBIA 2002) - of which this is the 16th event - is a meeting and discussion forum for arti?cial intelligence researchers and practitioners worldwide. SBIA is the leading c- ference in Brazil for the presentation of research and applications in arti?cial intelligence. The ?rst SBIA was held in 1984, and since 1995 it has been an international conference, with papers written in English and an international program committee, which this year was composed of 45 researchers from 13 countries. SBIA 2002 was held in conjunction with the VII Brazilian Symposium on Neural Networks (SBRN 2002). SBRN 2002 focuses on neural networks and on other models of computational intelligence. SBIA 2002, supported by the Brazilian Computer Society (SBC), was held in Porto de Galinhas/Recife, Brazil, 11-14 November 2002. The call for papers was very successful, resulting in 146 papers submitted from 18 countries. A total of 39 papers were accepted for publication in the proceedings. We would like to thank the SBIA 2002 sponsoring organizations, CNPq, Capes, and CESAR, and also all the authors who submitted papers. In particular, we would like to thank the program committee members and the additional referees for the di?cult task of reviewing and commenting on the submitted papers.

This volume contains the papers presented at the 13th Annual Conference on Algorithmic Learning Theory (ALT 2002), which was held in Lub * eck (Germany) during November 24-26, 2002. The main objective of the conference was to p- vide an interdisciplinary forum discussing the theoretical foundations of machine learning as well as their relevance to practical applications. The conference was colocated with the Fifth International Conference on Discovery Science (DS 2002). The volume includes 26 technical contributions which were selected by the program committee from 49 submissions. It also contains the ALT 2002 invited talks presented by Susumu Hayashi (Kobe University, Japan) on "e;Mathematics Based on Learning"e;, by John Shawe-Taylor (Royal Holloway University of L- don, UK) on "e;On the Eigenspectrum of the Gram Matrix and Its Relationship to the Operator Eigenspectrum"e;, and by Ian H. Witten (University of Waikato, New Zealand) on "e;Learning Structure from Sequences, with Applications in a Digital Library"e; (joint invited talk with DS 2002). Furthermore, this volume - cludes abstracts of the invited talks for DS 2002 presented by Gerhard Widmer (Austrian Research Institute for Arti?cial Intelligence, Vienna) on "e;In Search of the Horowitz Factor: Interim Report on a Musical Discovery Project"e; and by Rudolf Kruse (University of Magdeburg, Germany) on "e;Data Mining with Graphical Models"e;. The complete versions of these papers are published in the DS 2002 proceedings (Lecture Notes in Arti?cial Intelligence, Vol. 2534). ALT has been awarding the E.

This book constitutes the refereed proceedings of the 5th Catalonian Conference on Artificial Intelligence, CCIA 2002, held in Castellon, Spain in October 2002.The 37 revised full papers presented were carefully reviewed and selected from 77 submissions. The papers are organized in topical sections on reasoning models, constraint satisfation, machine learning and classification, multi-agent systems, and computer vision and robotics.

The Twelfth International Conference on Inductive Logic Programming was held in Sydney, Australia, July 9-11, 2002. The conference was colocated with two other events, the Nineteenth International Conference on Machine Learning (ICML2002) and the Fifteenth Annual Conference on Computational Learning Theory (COLT2002). Startedin1991,InductiveLogicProgrammingistheleadingannualforumfor researchers working in Inductive Logic Programming and Relational Learning. Continuing a series of international conferences devoted to Inductive Logic Programming and Relational Learning, ILP 2002 was the central event in 2002 for researchers interested in learning relational knowledge from examples. The Program Committee, following a resolution of the Community Me- ing in Strasbourg in September 2001, took upon itself the issue of the possible change of the name of the conference. Following an extended e-mail discussion, a number of proposed names were subjected to a vote. In the ?rst stage of the vote, two names were retained for the second vote. The two names were: Ind- tive Logic Programming, and Relational Learning. It had been decided that a 60% vote would be needed to change the name; the result of the vote was 57% in favor of the name Relational Learning. Consequently, the name Inductive Logic Programming was kept.

 This book constitutes the thoroughly refereed post-proceedings of the three agent-related workshops held during the NetObjectDays international conference, NODe 2002, held in Erfurt, Germany, in October 2002.The 23 revised full papers presented with a keynote paper and 2 abstracts were carefully selected during 2 rounds of reviewing and improvement. The papers are organized in topical sections on agent-oriented requirements engineering and specification, agent-oriented software engineering, reuse, negotiation and communication, large complex systems, e-business, and applications.

The 20 revised full papers presented in this book together with 4 section surveys were carefully reviewed and selected from the papers contributed to the 14th International Conference on Applications of Prolog, INAP 2001, held in Tokyo, Japan, in October 2002.The papers are devoted to the four tightly interwoven aspects knowledge acquisition, knowledge management, knowledge processing, and knowledge distribution, all in the context of the World Wide Web; they are organized in topical sections on Web languages and logic, knowlege acquisition and knowledge representation, decision support by advanced logic programming, and Web-knowledge management and data mining. The book is targeted to designers and users of e-business systems and e-government systems, for IT professionals who build such systems, as well as for the wider audience interested in the technical background of knowledge processing for the Web.

The characteristics of software systems are undergoing dramatic changes. We are moving rapidly into the age of ubiquitous information services. Persistent computing systems are being embedded in everyday objects. They interact in an autonomouswaywith eachother to provideus with increasinglycomplexservices and functionalities that we can access at any time from anywhere. As a con- quence, not only do the numbers of components of software systems increase; there is also a strong qualitative impact. Software systems are increasingly made up of autonomous, proactive, networked components. These interact with each other in patterns and via mechanisms that can hardly be modeled in terms of classical models of interaction or service-oriented coordination. To some extent, future software systems will exhibit characteristics making them more res- blant of natural systems and societies than of mechanical systems and software architectures. This situation poses exciting challenges to computer scientists and software engineers. Already, software agents and multi-agent systems are recognized as both useful abstractions and e?ective technologies for the modeling and building of complex distributed applications. However, little is done with regard to e?- tive and methodic development of complex software systems in terms of mul- agent societies. An urgent need exists for novel approaches to software modeling and software engineering that enable the successful deployment of software s- tems made up ofa massive number ofautonomous components, and that allowus to control and predict their behaviour.

The 7th Paci?c Asia Conference on Knowledge Discovery and Data Mining (PAKDD) was held from April 30 to May 2, 2003 in the Convention and Ex- bition Center (COEX), Seoul, Korea. The PAKDD conference is a major forum for academic researchers and industry practitioners in the Paci?c Asia region to share original research results and development experiences from di?erent KDD-related areas such as data mining, data warehousing, machine learning, databases, statistics, knowledge acquisition and discovery, data visualization, and knowledge-based systems. The conference was organized by the Advanced Information Technology Research Center (AITrc) at KAIST and the Statistical Research Center for Complex Systems (SRCCS) at Seoul National University. It was sponsored by the Korean Datamining Society (KDMS), the Korea Inf- mation Science Society (KISS), the United States Air Force O?ce of Scienti?c Research, the Asian O?ce of Aerospace Research & Development, and KAIST. It was held with cooperation from ACM's Special Group on Knowledge Dis- very and Data Mining (SIGKDD).