Current Trends in Connectionism

In order to build &quote;intelligent&quote; machines, many researchers have turned to the only naturally occurring intelligent system: the brain. For quite a while now, both the function and architecture of the brain have served as inspiration to philosophers, psychologists, computer scientists, neurobiologists, physicists and others in their quest for solving problems that seem to require intelligence in their own particular domain. The progress in the field of connectionism -- or artificial neural networks -- has had its ups and downs during its maturing years. Advocates of the field pointed out the virtues of connectionist systems, dealing with low-level cognitive tasks such as visual recognition and pattern completion, and inherent properties such as generalization, fault tolerance and parallel processing. However, research in the field virtually came to a halt at the end of the 1960s when Minsky and Papert published their critical analysis of connectionist systems, Perceptrons. In the beginning of the 1980s, the field was reborn with the appearance of new powerful learning methods which overcame many of the computational problems identified by Minsky and Papert. This volume is characterized by a number of different research directions distinguished by their perspectives on systems comprising interconnected sets of simple processing elements. Scientists who have strong backgrounds in neurobiology concentrate on the issues involved when modelling natural systems. Researchers with philosophical and psychological backgrounds stress other aspects which might not always be intuitively relevant to biology but instead are concerned with the mind and its higher-order cognitive capabilities. On the other hand, many researchers and engineers in industry take advantage of the wide applicability and mathematical properties of connectionist systems in order to solve practical problems, sacrificing even more of the principles underlying the basic idea of mimicking the function and architecture of the brain. None of these directions are right or wrong, but there has perhaps been too little exchange of knowledge and experience between them. The main purpose for organizing this conference was to bring together researchers with different backgrounds to exchange ideas and visions in the broad field of connectionism -- providing means for new insights that may push this area to another major breakthrough.

Auteur

Lars F. Niklasson, Mikael B. Bod,n

Contenu

Contents: Preface. D.S. Touretzky, A.D. Redish, Landmark Arrays and the Hippocampal Cognitive Map. M. Hasselmo, Physiological Constraints on Models of Behavior. E. Fransén, A. Lansner, Recurrent Attractor Neural Networks in Model of Cortical Associative Memory Function. J.R. Gobbel, A Biophysically-Based Model of the Neostriatum as Dynamically Reconfigurable Network. M. Garzon, F. Botelho, Dynamical Approximation by Neural Nets. M. Österberg, R. Lenz, On Parallel Selective Principal Component Analysis. M. Garzon, A. Jagota, Efficient Neural Net Isomorphism Testing. S.P. SikstrÖm, A. Lansner, The TECO Theory - Simulation of Recognition Failure. N. Sharkey, J. Neary, A. Sharkey, Searching Weight Space for Backpropagation Solution Types. M. Bodén, L. Niklasson, Features of Distributed Representations for Tree-structures: A Study of RAAM. N.B. Szirbik, G.L. Somlo, D.L. Buliga, Using the Conceptual Graph Model as Intermediate Representation for Knowledge Translation in Hybrid Systems. S.A. Jackson, N.E. Sharkey, Adaptive Generalization in Dynamic Neural Networks. A.J.C. Sharkey, N.E. Sharkey, O.C. Gopinath, Diversity, Neural Nets and Safety Critical Applications. O. Gällmo, J. CarlstrÖm, Some Experiments Using Extra Output Learning to Hint Multi Layer Perceptrons. J. CarlstrÖm, Minimization of Quantization Errors in Digital Implementations of Multi Layer Perceptrons. C. Balkenius, Multimodal Sensing for Motor Control. T. van Gelder, Modeling, Connectionist and Otherwise. R. Reilly, A Connectionist Exploration of the Computational Implications of Embodiment. T. Landelius, H. Knutsson, Behaviorism and Reinforcement Learning. E. Prem, Symbol Grounding and Transcedental Logic. R. Chrisley, A. Holland, Connectionist Synthetic Epistemology: Requirements for the Development of Objectivity. O.B. Coelho, Are Representations Still Necessary for Understanding Cognition? P. PylkkÖ, Indeterminacy and Experience. T. Vadén, The Symbolic-Subsymbolic Relation: From Limitivism to Correspondence. B. Bartell, G.W. Cottrell, R. Belew, Learning to Retrieve Information. T. Ziemke, F. Athley, Connectionist Models for the Detection of Oil Spills from Doppler Radar Imagery. M.C. Mozer, R.H. Dodier, M. Anderson, L. Vidmar, R.F. Cruickshank III, D. Miller, The Neural Network House: An Overview.