This book contains the proceedings of the International Confer ence on Artificial Neural Networks which was held between September 13 and 16 in Amsterdam. It is the third in a series which started two years ago in Helsinki and which last year took place in Brighton. Thanks to the European Neural Network Society, ICANN has emerged as the leading conference on neural networks in Europe. Neural networks is a field of research which has enjoyed a rapid expansion and great popularity in both the academic and industrial research communities. The field is motivated by the commonly held belief that applications in the fields of artificial intelligence and robotics will benefit from a good understanding of the neural information processing properties that underlie human intelligence. Essential aspects of neural information processing are highly parallel execution of com putation, integration of memory and process, and robustness against fluctuations. It is believed that intelligent skills, such as perception, motion and cognition, can be easier realized in neuro-computers than in a conventional computing paradigm. This requires active research in neurobiology to extract com putational principles from experimental neurobiological find ings, in physics and mathematics to study the relation between architecture and function in neural networks, and in cognitive science to study higher brain functions, such as language and reasoning. Neural networks technology has already lead to practical methods that solve real problems in a wide area of industrial applications. The clusters on robotics and applications contain sessions on various sub-topics in these fields.

The Self-Organizing Map (SOM), with its variants, is the most popular artificial neural network algorithm in the unsupervised learning category. About 4000 research articles on it have appeared in the open literature, and many industrial projects use the SOM as a tool for solving hard real world problems. Many fields of science have adopted the SOM as a standard analytical tool: statistics, signal processing, control theory, financial analyses, experimental physics, chemistry and medicine. This new edition includes a survey of over 2000 contemporary studies to cover the newest results. Case examples are provided with detailed formulae, illustrations, and tables. Further, a new chapter on software tools for SOM has been included whilst other chapters have been extended and reorganised.

This book contains the proceedings of the conference ANNIMAB-l, held 13-16 May 2000 in Goteborg, Sweden. The conference was organized by the Society for Artificial Neural Networks in Medicine and Biology (ANNIMAB-S), which was established to promote research within a new and genuinely cross-disciplinary field. Forty-two contributions were accepted for presentation; in addition to these, S invited papers are also included. Research within medicine and biology has often been characterised by application of statistical methods for evaluating domain specific data. The growing interest in Artificial Neural Networks has not only introduced new methods for data analysis, but also opened up for development of new models of biological and ecological systems. The ANNIMAB-l conference is focusing on some of the many uses of artificial neural networks with relevance for medicine and biology, specifically: • Medical applications of artificial neural networks: for better diagnoses and outcome predictions from clinical and laboratory data, in the processing of ECG and EEG signals, in medical image analysis, etc. More than half of the contributions address such clinically oriented issues. • Uses of ANNs in biology outside clinical medicine: for example, in models of ecology and evolution, for data analysis in molecular biology, and (of course) in models of animal and human nervous systems and their capabilities. • Theoretical aspects: recent developments in learning algorithms, ANNs in relation to expert systems and to traditional statistical procedures, hybrid systems and integrative approaches.

Innovations in Intelligent Systems is a rare collection of the latest developments in intelligent paradigms such as knowledge-based systems, computational intelligence and hybrid combinations as well as practical applications in engineering, science, business and commerce. The book covers central topics such as intelligent multi-agent systems, data mining, case-based reasoning, and rough sets. Essential techniques to the development of intelligent machines are investigated such as pattern recognition and classification, machine learning, natural language processing, grammar, evolutionary schemes, fuzzy-neural procedures, and intelligent vision. The book also includes useful applications ranging from medical diagnosis and technical/medical language translation, to power demand forecasting and manufacturing plants. Due to its depth and breadth of the coverage and the usefulness of the techniques and applications, this book is a valuable reference for experts and students alike.

November 28-December 1, 1994, Denver, Colorado NIPS is the longest running annual meeting devoted to Neural Information Processing Systems. Drawing on such disparate domains as neuroscience, cognitive science, computer science, statistics, mathematics, engineering, and theoretical physics, the papers collected in the proceedings of NIPS7 reflect the enduring scientific and practical merit of a broad-based, inclusive approach to neural information processing. The primary focus remains the study of a wide variety of learning algorithms and architectures, for both supervised and unsupervised learning. The 139 contributions are divided into eight parts: Cognitive Science, Neuroscience, Learning Theory, Algorithms and Architectures, Implementations, Speech and Signal Processing, Visual Processing, and Applications. Topics of special interest include the analysis of recurrent nets, connections to HMMs and the EM procedure, and reinforcement- learning algorithms and the relation to dynamic programming. On the theoretical front, progress is reported in the theory of generalization, regularization, combining multiple models, and active learning. Neuroscientific studies range from the large-scale systems such as visual cortex to single-cell electrotonic structure, and work in cognitive scientific is closely tied to underlying neural constraints. There are also many novel applications such as tokamak plasma control, Glove-Talk, and hand tracking, and a variety of hardware implementations, with particular focus on analog VLSI.

Feed-Forward Neural Networks: Vector Decomposition Analysis, Modelling and Analog Implementation presents a novel method for the mathematical analysis of neural networks that learn according to the back-propagation algorithm. The book also discusses some other recent alternative algorithms for hardware implemented perception-like neural networks. The method permits a simple analysis of the learning behaviour of neural networks, allowing specifications for their building blocks to be readily obtained. Starting with the derivation of a specification and ending with its hardware implementation, analog hard-wired, feed-forward neural networks with on-chip back-propagation learning are designed in their entirety. On-chip learning is necessary in circumstances where fixed weight configurations cannot be used. It is also useful for the elimination of most mis-matches and parameter tolerances that occur in hard-wired neural network chips. Fully analog neural networks have several advantages over other implementations: low chip area, low power consumption, and high speed operation. Feed-Forward Neural Networks is an excellent source of reference and may be used as a text for advanced courses.