We would like to present, with great pleasure, the ?rst volume of a new jo- nal, Transactions on Rough Sets. This journal, part of the new journal subline in the Springer-Verlag series Lecture Notes in Computer Science, is devoted to the entire spectrum of rough set related issues, starting from logical and ma- ematical foundations of rough sets, through all aspects of rough set theory and its applications, data mining, knowledge discovery and intelligent information processing, to relations between rough sets and other approaches to uncertainty, vagueness, and incompleteness, such as fuzzy sets, theory of evidence, etc. The ?rst, pioneering papers on rough sets, written by the originator of the idea, ProfessorZdzis lawPawlak, werepublishedintheearly1980s.Weareproud to dedicate this volume to our mentor, Professor Zdzis law Pawlak, who kindly enriched this volume with his contribution on philosophical, logical, and mat- matical foundations of roughset theory. In his paper Professor Pawlakshows all over again the underlying ideas of rough set theory as well as its relations with Bayes' theorem, con?ict analysis, ?ow graphs, decision networks, and decision rules.

This volume contains papers presented at the 17th Annual Conference on Le- ning Theory (previously known as the Conference on Computational Learning Theory) held in Ban?, Canada from July 1 to 4, 2004. The technical program contained 43 papers selected from 107 submissions, 3 open problems selected from among 6 contributed, and 3 invited lectures. The invited lectures were given by Michael Kearns on 'Game Theory, Automated Trading and Social Networks', Moses Charikar on 'Algorithmic Aspects of - nite Metric Spaces', and Stephen Boyd on 'Convex Optimization, Semide?nite Programming, and Recent Applications'. These papers were not included in this volume. The Mark Fulk Award is presented annually for the best paper co-authored by a student. Thisyear theMark Fulk award wassupplemented with two further awards funded by the Machine Learning Journal and the National Information Communication Technology Centre, Australia (NICTA). We were therefore able toselectthreestudentpapersforprizes.ThestudentsselectedwereMagalieF- montforthesingle-authorpaper"ModelSelectionbyBootstrapPenalizationfor Classi?cation", Daniel Reidenbach for the single-author paper "On the Lear- bility of E-Pattern Languages over Small Alphabets", and Ran Gilad-Bachrach for the paper "Bayes and Tukey Meet at the Center Point" (co-authored with Amir Navot and Naftali Tishby).

Automatic Quantum Computer Programming provides an introduction to quantum computing for non-physicists, as well as an introduction to genetic programming for non-computer-scientists. The book explores several ways in which genetic programming can support automatic quantum computer programming and presents detailed descriptions of specific techniques, along with several examples of their human-competitive performance on specific problems. Source code for the author 's QGAME quantum computer simulator is included as an appendix, and pointers to additional online resources furnish the reader with an array of tools for automatic quantum computer programming.

The fusion of di?erent information sourcesis a persistent and intriguing issue. It hasbeenaddressedforcenturiesinvariousdisciplines, includingpoliticalscience, probability and statistics, system reliability assessment, computer science, and distributed detection in communications. Early seminal work on fusion was c- ried out by pioneers such as Laplace and von Neumann. More recently, research activities in information fusion have focused on pattern recognition. During the 1990s, classi?erfusionschemes, especiallyattheso-calleddecision-level, emerged under a plethora of di?erent names in various scienti?c communities, including machine learning, neural networks, pattern recognition, and statistics. The d- ferent nomenclatures introduced by these communities re?ected their di?erent perspectives and cultural backgrounds as well as the absence of common forums and the poor dissemination of the most important results. In 1999, the ?rst workshop on multiple classi?er systems was organized with the main goal of creating a common international forum to promote the diss- ination of the results achieved in the diverse communities and the adoption of a common terminology, thus giving the di?erent perspectives and cultural ba- grounds some concrete added value. After ?ve meetings of this workshop, there is strong evidence that signi?cant steps have been made towards this goal. - searchers from these diverse communities successfully participated in the wo- shops, and world experts presented surveys of the state of the art from the perspectives of their communities to aid cross-fertilizat

This four-volume set of LNCS 12821, LNCS 12822, LNCS 12823 and LNCS 12824, constitutes the refereed proceedings of the 16th International Conference on Document Analysis and Recognition, ICDAR 2021, held in Lausanne, Switzerland in September 2021. The 182 full papers were carefully reviewed and selected from 340 submissions, and are presented with 13 competition reports. The papers are organized into the following topical sections: scene text detection and recognition, document classification, gold-standard benchmarks and data sets, historical document analysis, and handwriting recognition. In addition, the volume contains results of 13 scientific competitions held during ICDAR 2021.

This four-volume set of LNCS 12821, LNCS 12822, LNCS 12823 and LNCS 12824, constitutes the refereed proceedings of the 16th International Conference on Document Analysis and Recognition, ICDAR 2021, held in Lausanne, Switzerland in September 2021. The 182 full papers were carefully reviewed and selected from 340 submissions, and are presented with 13 competition reports. The papers are organized into the following topical sections: extracting document semantics, text and symbol recognition, document analysis systems, office automation, signature verification, document forensics and provenance analysis, pen-based document analysis, human document interaction, document synthesis, and graphs recognition.

The field called Learning Classifier Systems is populated with romantics. Why shouldn't it be possible for computer programs to adapt, learn, and develop while interacting with their environments? In particular, why not systems that, like organic populations, contain competing, perhaps cooperating, entities evolving together? John Holland was one of the earliest scientists with this vision, at a time when so-called artificial intelligence was in its infancy and mainly concerned with preprogrammed systems that didn't learn. that, like organisms, had sensors, took Instead, Holland envisaged systems actions, and had rich self-generated internal structure and processing. In so doing he foresaw and his work prefigured such present day domains as reinforcement learning and embedded agents that are now displacing the older "standard Af' . One focus was what Holland called "classifier systems" sets of competing rule like "classifiers," each a hypothesis as to how best to react to some aspect of the environment--or to another rule. The system embracing such a rule "popu lation" would explore its available actions and responses, rewarding and rating the active rules accordingly. Then "good" classifiers would be selected and re produced, mutated and even crossed, a la Darwin and genetics, steadily and reliably increasing the system's ability to cope."

Computational learning theory is one of the first attempts to construct a mathematical theory of a cognitive process. It has been a field of much interest and rapid growth in recent years. This text provides a framework for studying a variety of algorithmic processes, such as those currently in use for training artificial neural networks. The authors concentrate on an approximate model for learning and gradually develop the ideas of efficiency considerations. Finally, they consider applications of the theory to artificial neural networks. An abundance of exercises and an extensive list of references round out the text. This volume provides a comprehensive review of the topic, including information drawn from logic, probability, and complexity theory. It forms a solid introduction to the theory of comptutational learning suitable for a broad spectrum of graduate students from theoretical computer science to mathematics.

Frontiers of Evolutionary Computation brings together eleven contributions by international leading researchers discussing what significant issues still remain unresolved in the field of Evolutionary Computation (EC). They explore such topics as the role of building blocks, the balancing of exploration with exploitation, the modeling of EC algorithms, the connection with optimization theory and the role of EC as a meta-heuristic method, to name a few. The articles feature a mixture of informal discussion interspersed with formal statements, thus providing the reader an opportunity to observe a wide range of EC problems from the investigative perspective of world-renowned researchers. These prominent researchers include:
-Heinz MA1/4hlenbein,
-Kenneth De Jong,
-Carlos Cotta and Pablo Moscato,
-Lee Altenberg,
-Gary A. Kochenberger, Fred Glover, Bahram Alidaee and Cesar Rego,
-William G. Macready,
-Christopher R. Stephens and Riccardo Poli,
-Lothar M. Schmitt,
-John R. Koza, Matthew J. Street and Martin A. Keane,
-Vivek Balaraman,
-Wolfgang Banzhaf and Julian Miller.

Frontiers of Evolutionary Computation is ideal for researchers and students who want to follow the process of EC problem-solving and for those who want to consider what frontiers still await their exploration.

In this volume we present the accepted contributions for the 7th European C- ference on Genetic Programming (EuroGP 2004). The conference took place on 5 7 April 2004 in Portugal at the University of Coimbra, in the Department of Mathematics in Pra, ca Dom Dinis, located on the hill above the old town. EuroGP is a well-established conference and the sole one exclusively de- ted to Genetic Programming. Previous proceedings have all been published by Springer-Verlag in the LNCS series. EuroGP began as an international wor- hop in Paris, France in 1998 (14 15 April, LNCS 1391). Subsequently the wor- hop was held in G] oteborg, Sweden in 1999 (26 27 May, LNCS 1598) and then EuroGP became an annual conference: in 2000 in Edinburgh, UK (15 16 April, LNCS 1802), in 2001 at Lake Como, Italy (18 19 April, LNCS 2038), in 2002 in Kinsale, Ireland (3 5 April, LNCS 2278), and in 2003 in Colchester, UK (14 16 April, LNCS 2610). From the outset, there have always been specialized wor- hops, co-located with EuroGP, focusing on applications of evolutionary al- rithms (LNCS 1468, 1596, 1803, 2037, 2279, and 2611). This year the EvoCOP workshop on combinatorial optimization transformed itself into a conference in its own right, and the two conferences, together with the EvoWorkshops, EvoBIO, EvoIASP, EvoMUSART, EvoSTOC, EvoHOT, and EvoCOMNET, now form one of the largest events dedicated to Evolutionary Computation in Europe."

The Distinguished Dissertations series is published on behalf of the Conference of Professors and Heads of Computing and the British Computer Society, who annually select the best British PhD dissertations in computer science for publication. The dissertations are selected on behalf of the CPHC by a panel of eight academics. Each dissertation chosen makes a noteworthy contribution to the subject and reaches a high standard of exposition, placing all results clearly in the context of computer science as a whole. In this way computer scientists with significantly different interests are able to grasp the essentials - or even find a means of entry - to an unfamiliar research topic. Machine learning promises both to create machine intelligence and to shed light on natural intelligence. A fundamental issue for either endevour is that of credit assignment, which we can pose as follows: how can we credit individual components of a complex adaptive system for their often subtle effects on the world? For example, in a game of chess, how did each move (and the reasoning behind it) contribute to the outcome? This text studies aspects of credit assignment in learning classifier systems, which combine evolutionary algorithms with reinforcement learning methods to address a range of tasks from pattern classification to stochastic control to simulation of learning in animals. Credit assignment in classifier systems is complicated by two features: 1) their components are frequently modified by evolutionary search, and 2) components tend to interact. Classifier systems are re-examined from first principles and the result is, primarily, a formalization of learning in these systems, and a body of theoryrelating types of classifier systems, learning tasks, and credit assignment pathologies. Most significantly, it is shown that both of the main approaches have difficulties with certain tasks, which the other type does not.

Genetic Programming Theory and Practice explores the emerging interaction between theory and practice in the cutting-edge, machine learning method of Genetic Programming (GP). The material contained in this contributed volume was developed from a workshop at the University of Michigan's Center for the Study of Complex Systems where an international group of genetic programming theorists and practitioners met to examine how GP theory informs practice and how GP practice impacts GP theory. The contributions cover the full spectrum of this relationship and are written by leading GP theorists from major universities, as well as active practitioners from leading industries and businesses. Chapters include such topics as John Koza's development of human-competitive electronic circuit designs; David Goldberg's application of "competent GA" methodology to GP; Jason Daida's discovery of a new set of factors underlying the dynamics of GP starting from applied research; and Stephen Freeland's essay on the lessons of biology for GP and the potential impact of GP on evolutionary theory.

1 feel privileged that the J(jh Advances in Computer Games Conference (ACG 10) takes place in Graz, Styria, Austria. It is the frrst time that Austria acts as host country for this major event. The series of conferences started in Edinburgh, Scotland in 1975 and was then held four times in England, three times in The Netherlands, and once in Germany. The ACG-10 conference in Graz is special in that it is organised together with the 11th World Computer Chess Championship (WCCC), the Sth Computer Olympiad (CO), and the European Union Y outh Chess Championship. The 11 th WCCC and ACG 10 take place in the Dom im Berg (Dome in the Mountain), a high-tech space with multimedia equipment, located in the Schlossberg, in the centre of the city. The help of many sponsors (large and small) is gratefully acknowledged. They will make the organisation of this conference a success. In particular, 1 would like to thank the European Union for designating Graz as the Cultural Capital of Europe 2003. There are 24 accepted contributions by participants from all over the world: Europe, Japan, USA, and Canada. The specific research results ofthe ACG 10 are expected to tind their way to general applications. The results are described in the pages that follow. The international stature together with the technical importance of this conference reaffrrms the mandate of the International Computer Games Association (ICGA) to represent the computer-games community."

The 5th International Workshop on Learning Classi?er Systems (IWLCS2002) was held September 7-8, 2002, in Granada, Spain, during the 7th International Conference on Parallel Problem Solving from Nature (PPSN VII). We have included in this volume revised and extended versions of the papers presented at the workshop. In the ?rst paper, Browne introduces a new model of learning classi?er system, iLCS, and tests it on the Wisconsin Breast Cancer classi?cation problem. Dixon et al. present an algorithm for reducing the solutions evolved by the classi?er system XCS, so as to produce a small set of readily understandable rules. Enee and Barbaroux take a close look at Pittsburgh-style classi?er systems, focusing on the multi-agent problem known as El-farol. Holmes and Bilker investigate the effect that various types of missing data have on the classi?cation performance of learning classi?er systems. The two papers by Kovacs deal with an important theoretical issue in learning classi?er systems: the use of accuracy-based ?tness as opposed to the more traditional strength-based ?tness. In the ?rst paper, Kovacs introduces a strength-based version of XCS, called SB-XCS. The original XCS and the new SB-XCS are compared in the second paper, where - vacs discusses the different classes of solutions that XCS and SB-XCS tend to evolve.

Networks of Learning Automata: Techniques for Online Stochastic Optimization is a comprehensive account of learning automata models with emphasis on multiautomata systems. It considers synthesis of complex learning structures from simple building blocks and uses stochastic algorithms for refining probabilities of selecting actions. Mathematical analysis of the behavior of games and feedforward networks is provided. Algorithms considered here can be used for online optimization of systems based on noisy measurements of performance index. Also, algorithms that assure convergence to the global optimum are presented. Parallel operation of automata systems for improving speed of convergence is described. The authors also include extensive discussion of how learning automata solutions can be constructed in a variety of applications.

This volume contains the papers presented at the 14th Annual Conference on Algorithmic Learning Theory (ALT 2003), which was held in Sapporo (Japan) duringOctober17-19,2003. Themainobjectiveoftheconferencewastoprovide an interdisciplinary forum for discussing the theoretical foundations of machine learning as well as their relevance to practical applications. The conference was co-locatedwiththe6thInternationalConferenceonDiscoveryScience(DS2003). The volume includes 19 technical contributions that were selected by the program committee from 37 submissions. It also contains the ALT 2003 invited talks presented by Naftali Tishby (Hebrew University, Israel) on "E?cient Data Representations that Preserve Information," by Thomas Zeugmann (University of Lub ] eck, Germany) on "Can Learning in the Limit be Done E?ciently?," and by Genshiro Kitagawa (Institute of Statistical Mathematics, Japan) on "S- nal Extraction and Knowledge Discovery Based on Statistical Modeling" (joint invited talk with DS 2003). Furthermore, this volume includes abstracts of the invitedtalksforDS2003presentedbyThomasEiter(ViennaUniversityofTe- nology, Austria) on "Abduction and the Dualization Problem" and by Akihiko Takano (National Institute of Informatics, Japan) on "Association Computation for Information Access. " The complete versions of these papers were published in the DS 2003 proceedings (Lecture Notes in Arti?cial Intelligence Vol. 2843). ALT has been awarding theE. MarkGoldAward for the most outstanding paper by a student author since 1999. This year the award was given to Sandra Zilles for her paper "Intrinsic Complexity of Uniform Learning. " This conference was the 14th in a series of annual conferences established in 1990. ContinuationoftheALTseriesissupervisedbyitssteeringcommittee, c- sisting of: Thomas Zeugmann (Univ."

Exploration of Visual Data presents latest research efforts in the area of content-based exploration of image and video data. The main objective is to bridge the semantic gap between high-level concepts in the human mind and low-level features extractable by the machines.

The two key issues emphasized are "content-awareness" and "user-in-the-loop." The authors provide a comprehensive review on algorithms for visual feature extraction based on color, texture, shape, and structure, and techniques for incorporating such information to aid browsing, exploration, search, and streaming of image and video data. They also discuss issues related to the mixed use of textual and low-level visual features to facilitate more effective access of multimedia data.

To bridge the semantic gap, significant recent research efforts have also been put on learning during user interactions, which is also known as "relevance feedback." The difficulty and challenge also come from the personalized information need of each user and a small amount of feedbacks the machine could obtain through real-time user interaction. The authors present and discuss several recently proposed classification and learning techniques that are specifically designed for this problem, with kernel- and boosting-based approaches for nonlinear extensions.

Exploration of Visual Data provides state-of-the-art materials on the topics of content-based description of visual data, content-based low-bitrate video streaming, and latest asymmetric and nonlinear relevance feedback algorithms, which to date are unpublished.

Exploration of Visual Data will be of interest to researchers, practitioners, and graduate-level students in theareas of multimedia information systems, multimedia databases, computer vision, machine learning.

The proceedings of ECML/PKDD2003 are published in two volumes: the P- ceedings of the 14th European Conference on Machine Learning (LNAI 2837) and the Proceedings of the 7th European Conference on Principles and Practice of Knowledge Discovery in Databases (LNAI 2838). The two conferences were held on September 22-26, 2003 in Cavtat, a small tourist town in the vicinity of Dubrovnik, Croatia. As machine learning and knowledge discovery are two highly related ?elds, theco-locationofbothconferencesisbene?cialforbothresearchcommunities.In Cavtat, ECML and PKDD were co-located for the third time in a row, following the successful co-location of the two European conferences in Freiburg (2001) and Helsinki (2002). The co-location of ECML2003 and PKDD2003 resulted in a joint program for the two conferences, including paper presentations, invited talks, tutorials, and workshops. Out of 332 submitted papers, 40 were accepted for publication in the ECML2003proceedings, and40wereacceptedforpublicationinthePKDD2003 proceedings. All the submitted papers were reviewed by three referees. In ad- tion to submitted papers, the conference program consisted of four invited talks, four tutorials, seven workshops, two tutorials combined with a workshop, and a discovery challenge

This volume contains papers presented at the joint 16th Annual Conference on Learning Theory (COLT) and the 7th Annual Workshop on Kernel Machines, heldinWashington, DC, USA, duringAugust24 27,2003.COLT, whichrecently merged with EuroCOLT, has traditionally been a meeting place for learning theorists. We hope that COLT will bene't from the collocation with the annual workshoponkernelmachines, formerlyheldasaNIPSpostconferenceworkshop. The technical program contained 47 papers selected from 92 submissions. All 47paperswerepresentedasposters;22ofthepaperswereadditionallypresented astalks.Therewerealsotwotargetareaswithinvitedcontributions.Incompu- tional game theory, atutorialentitled LearningTopicsinGame-TheoreticDe- sionMaking wasgivenbyMichaelLittman, andaninvitedpaperon AGeneral Class of No-Regret Learning Algorithms and Game-Theoretic Equilibria was contributed by Amy Greenwald. In natural language processing, a tutorial on Machine Learning Methods in Natural Language Processing was presented by Michael Collins, followed by two invited talks, Learning from Uncertain Data by Mehryar Mohri and Learning and Parsing Stochastic Uni?cation- Based Grammars by Mark Johnson. In addition to the accepted papers and invited presentations, we solicited short open problems that were reviewed and included in the proceedings. We hope that reviewed open problems might become a new tradition for COLT. Our goal was to select simple signature problems whose solutions are likely to inspire further research. For some of the problems the authors o?ered monetary rewards. Yoav Freund acted as the open problem area chair. The open problems were presented as posters at the conference."

Two key words for mechanical engineering in the future are Micro and Intelligence. It is weIl known that the leadership in the intelligence technology is a marter of vital importance for the future status of industrial society, and thus national research projects for intelligent materials, structures and machines have started not only in advanced countries, but also in developing countries. Materials and structures which have self-sensing, diagnosis and actuating systems, are called intelligent or smart, and are of growing research interest in the world. In this situation, the IUT AM symposium on Dynamics 0/ Advanced Materials and Smart Structures was a timely one. Smart materials and structures are those equipped with sensors and actuators to achieve their designed performance in achanging environment. They have complex structural properties and mechanical responses. Many engineering problems, such as interface and edge phenomena, mechanical and electro-magnetic interaction/coupling and sensing, actuating and control techniques, arise in the development ofintelligent structures. Due to the multi-disciplinary nature ofthese problems, all ofthe classical sciences and technologies, such as applied mathematics, material science, solid and fluid mechanics, control techniques and others must be assembled and used to solve them. IUTAM weIl understands the importance ofthis emerging technology. An IUTAM symposium on Smart Structures and Structronic Systems (Chaired by U.

This book constitutes the refereed proceedings of the Third International Conference on Machine Learning and Data Mining in Pattern Recognition, MLDM 2003, held in Leipzig, Germany, in July 2003. The 33 revised full papers presented together with two invited papers were carefully reviewed and selected from 75 submissions. The papers are organized in topical sections on decision trees; clustering and its applications; support vector machines; case-based reasoning; classification, retrieval, and feature Learning; discovery of frequent or sequential patterns; Bayesian models and methods; association rule mining; and applications.

Grammatical Evolution: Evolutionary Automatic Programming in an Arbitrary Language provides the first comprehensive introduction to Grammatical Evolution, a novel approach to Genetic Programming that adopts principles from molecular biology in a simple and useful manner, coupled with the use of grammars to specify legal structures in a search. Grammatical Evolution's rich modularity gives a unique flexibility, making it possible to use alternative search strategies - whether evolutionary, deterministic or some other approach - and to even radically change its behavior by merely changing the grammar supplied. This approach to Genetic Programming represents a powerful new weapon in the Machine Learning toolkit that can be applied to a diverse set of problem domains.

This book constitutes the refereed proceedings of the 6th European Conference on Genetic Programming, EuroGP 2003, held in Essex, UK in April 2003. The 45 revised papers presented were carefully reviewed and selected from 61 submissions. All current aspects of genetic programming and genetic algorithms are addressed, ranging from foundational, theoretical, and methodological issues to advanced applications in various fields.

Genetic Algorithms: Principles and Perspectives: A Guide to GA Theory is a survey of some important theoretical contributions, many of which have been proposed and developed in the Foundations of Genetic Algorithms series of workshops. However, this theoretical work is still rather fragmented, and the authors believe that it is the right time to provide the field with a systematic presentation of the current state of theory in the form of a set of theoretical perspectives. The authors do this in the interest of providing students and researchers with a balanced foundational survey of some recent research on GAs. The scope of the book includes chapter-length discussions of Basic Principles, Schema Theory, "No Free Lunch," GAs and Markov Processes, Dynamical Systems Model, Statistical Mechanics Approximations, Predicting GA Performance, Landscapes and Test Problems.

Learning and Generalization provides a formal mathematical theory for addressing intuitive questions of the type: * How does a machine learn a new concept on the basis of examples? * How can a neural network, after sufficient training, correctly predict the outcome of a previously unseen input? * How much training is required to achieve a specified level of accuracy in the prediction? * How can one identify the dynamical behaviour of a nonlinear control system by observing its input-output behaviour over a finite interval of time? The first edition, A Theory of Learning and Generalization, was the first book to treat the problem of machine learning in conjunction with the theory of empirical process, the latter being a well-established branch of probability theory. The treatment of both topics side-by-side leads to new insights, as well as new results in both topics. The second edition extends and improves upon this material, covering new areas including: * Support vector machines (SVM's) * Fat-shattering dimensions and applications to neural network learning * Learning with dependent samples generated by a beta-mixing process * Connections between system identification and learning theory * Probabilistic solution of 'intractable problems' in robust control and matrix theory using randomized algorithms It also contains solutions to some of the open problems posed in the first edition, while adding new open problems. This book is essential reading for control and system theorists, neural network researchers, theoretical computer scientists and probabilists The Communications and Control Engineering series reflects the major technological advances which have a great impact in the fields of communication and control. It reports on the research in industrial and academic institutions around the world to exploit the new possibilities which are becoming available