ICANN ’93

1. Front Matter

   Pages i-xxvii

   PDF

2. Plenary Contributions

   1. Front Matter

      Pages 1-1

      PDF

   2. Dynamic Coupling in Cortical Neural Networks

      • Ad Aertsen

      Pages 3-10

   3. Keeping Neural Networks Simple

      • Geoffrey E. Hinton, Drew van Camp

      Pages 11-18

3. Principles from Neurobiology

   1. Front Matter

      Pages 19-19

      PDF

   2. Memory and selforganization —oral contributions

      1. The Autoassociative Hypothesis Places Constraints on Hippocampal Organization

         • Alessandro Treves, Edmund T. Rolls

         Pages 21-26

      2. Metastability of Network Attractor and Dream Sleep

         • Mitsuyuki Nakao, Kazuhiko Watanabe, Yoshinari Mizutani, Mitsuaki Yamamoto

         Pages 27-30

      3. Somatosensory Cortical Maps: Reorganization Following Post-Ontogenetic Plasticity — Experiments and Theory

         • Sylvie Wacquant, Frank Joublin, Friederike Spengler, Ben Godde, Hubert R. Dinse

         Pages 31-36

      4. Adequate Input for Learning in Attractor Neural Networks

         • Daniel J. Amit, Nicolas Brunel

         Pages 37-41

   3. Memory and selforganization —poster contributions

      1. Neurobiological Modelling and Structured Neural Networks

         • B. Brückner, W. Zander

         Pages 43-46

      2. Model Analysis of Associative Learning in The Photoreceptor of Marine Mollusc, <i>Hermissenda Crassicornis</i>

         • Hidetoshi Ikeno, Shiro Usui

         Pages 47-50

      3. A Neural Network Model for Motor Shapes Learning and Programming

         • J. L. Velay, J. C. Gilhodes, B. Ans, Y. Coiton

         Pages 51-54

      4. Learning Through Adaptive Value: A Model Working in a Variable Environment

         • A. Murciano, J. Zamora

         Pages 55-58

      5. Improving Categorization with CALM Maps

         • Ed Lebert, R. Hans Phaf

         Pages 59-62

      6. A Simple Selforganizing Neural Network Architecture for Selective Visual Attention

         • D. Heinke, H.-M. Gross

         Pages 63-66

      7. Detection of Coincidences and Generation of Hypotheses — a Proposal for an Elementary Cortical Function

         • R. Moeller, H.-M. Gross

         Pages 67-70

      8. DIVA: A Self-organizing Neural Network Model for Motor Equivalent Speech Production

         • Frank H. Guenther

         Pages 71-74

      9. Adaptive Non-Uniform A/D Conversion Achieved with an Unsupervised Learning Rule Maximizing Information-Theoretic Entropy

         • Marc M. van Hulle

         Pages 75-75

      10. Optimal Topology-Preservation Using Self-Organising Logical Neural Networks

          • G. Tambouratzis, T. J. Stonham

          Pages 76-79

      11. Incorporation of Neurobiological Aspects of <i>Aplysia’s</i> Associative Conditioning in Neural Networks for on-line Pattern Detection

          • M. H. Spigt, D. S. Brée, M. Nielen

          Pages 80-80

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.

• artificial intelligence
• artificial neural network
• brain
• cognition
• dynamical systems
• information processing
• intelligence
• neural network
• neural networks
• neurobiology
• neurons
• pattern
• pattern recognition
• robot
• robotics

• Dutch Foundation for Neural Networks, University of Nijmegen, Nijmegen, The Netherlands

  Stan Gielen, Bert Kappen

Policies and ethics