This volume reflects the state of the art in artificial intelligence in the Australasian region. It covers machine learning, knowledge acguisition, cognitive modelling, robots and vision, natural language, automated reasoning, knowledge-based systems, neural networks and genetic algorithms, distributed AI, etc.

Rules – the clearest, most explored and best understood form of knowledge representation – are particularly important for data mining, as they offer the best tradeoff between human and machine understandability. This book presents the fundamentals of rule learning as investigated in classical machine learning and modern data mining. It introduces a feature-based view, as a unifying framework for propositional and relational rule learning, thus bridging the gap between attribute-value learning and inductive logic programming, and providing complete coverage of most important elements of rule learning. The book can be used as a textbook for teaching machine learning, as well as a comprehensive reference to research in the field of inductive rule learning. As such, it targets students, researchers and developers of rule learning algorithms, presenting the fundamental rule learning concepts in sufficient breadth and depth to enable the reader to understand, develop and apply rule learning techniques to real-world data.

In the areas of industry and engineering, AI techniques have become the norm in sectors including computer-aided design, intelligent manufacturing, and control. Papers in this volume represent work by both computer scientists and engineers separately and together. They directly and indirectly represent a real collaboration between computer science and engineering, covering a wide variety of fields related to intelligent systems technology ranging from neural networks, knowledge acquisition and representation, automated scheduling, machine learning, multimedia, genetic algorithms, fuzzy logic, robotics, automated reasoning, heuristic searching, automated problem solving, temporal, spatial and model-based reasoning, clustering, blackboard architectures, automated design, pattern recognition and image processing, automated planning, speech recognition, simulated annealing, and intelligent tutoring, as well as various computer applications of intelligent systems including financial analysis, artificial

This book constitutes the refereed proceedings of the 17th Australian Conference on Artificial Intelligence, AI 2004, held in Cairns, Australia, in December 2004. The 78 revised full papers and 62 revised short papers presented were carefully reviewed and selected from 340 submissions. The papers are organized in topical sections on agents; biomedical applications; computer vision, image processing, and pattern recognition; ontologies, knowledge discovery and data mining; natural language and speech processing; problem solving and reasoning; robotics; and soft computing.

AISC 2002, the 6th international conference on Arti?cial Intelligence and S- bolic Computation, and Calculemus 2002, the 10th symposium on the Integ- tion of Symbolic Computation and Mechanized Reasoning, were held jointly in Marseille, France on July 1-5, 2002. This event was organized by the three universities in Marseille together with the LSIS (Laboratoire des Sciences de l'Information et des Syst` emes). AISC 2002 was the latest in a series of specialized conferences founded by John Campbell and Jacques Calmet with the initial title "Arti?cial Intelligence and Symbolic Mathematical Computation" (AISMC) and later denoted "Art- cial Intelligence and Symbolic Computation" (AISC). The scope is well de?ned by its successive titles. AISMC-1 (1992), AISMC-2 (1994), AISMC-3 (1996), AISC'98, and AISC 2000 took place in Karlsruhe, Cambridge, Steyr, Plattsburgh (NY), and Madrid respectively. The proceedings were published by Springer-Verlag as LNCS 737, LNCS 958, LNCS 1138, LNAI 1476, and LNAI 1930 respectively. Calculemus 2002 was the 10th symposium in a series which started with three meetings in 1996, two meetings in 1997, and then turned into a yearly event in 1998. Since then, it has become a tradition to hold the meeting jointly with an event in either symbolic computation or automated deduction. Both events share common interests in looking at Symbolic Computation, each from a di?erent point of view: Arti?cial Intelligence in the more general case of AISC and Automated Deduction in the more speci?c case of Calculemus.

The Portuguese Association for Arti cial Intelligence (APPIA) has been re- larly organising the Portuguese Conference on Arti cial Intelligence (EPIA). This ninth conference follows previous ones held in Porto (1985), Lisboa (1986), Braga (1987), Lisboa (1989), Albufeira (1991), Porto (1993), Funchal (1995) and Coimbra (1997). Starting in 1989, the conferences have been held biennially (alternating with an APPIA Advanced School on Arti cial Intelligence) and become truly international: English has been adopted as the o cial language and the proceedings are published in Springer’s LNAI series. The conference has recon rmed its high international standard this year, largely due to its programme committee, composed of distinguished researchers in a variety of specialities in Arti cial Intelligence, half of them from Portuguese universities. This has attracted a signi cant international interest, well expressed by the number of papers submitted (66), from 17 di erent countries, 29 of which are by Portuguese researchers. From the 66 papers submitted, about one third of them (23) were selected for oral presentation and have been published in this volume. The review process enabled the selection of high quality papers, each paper being reviewed by two or three reviewers, either from the programme committee or by their appointment. We would like to thank all of the reviewers for their excellent and hard work.

Designing is one of the most significant of human acts. Surprisingly, given that designing has been occurring for many millenia, our understanding of the processes of designing is remarkably limited. Recently, design methods have been formalised not as humano-centred processes but as processes capable of computer implementation with the goal of augmenting human designers. This volume contains contributions which cover design methods based on evolutionary systems, generative processes, evaluation methods and analysis methods. It presents the state of the art in formal design methods for computer aided design.