Current Trends in Connectionism: Proceedings

In order to build "intelligent" 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.

Preface	p. vii
Introduction	p. 1
Landmark Arrays and the Hippocampal Cognitive Map	p. 1
Conclusions	p. 11
References	p. 13
Physiological Constraints on Models of Behavior	p. 15
Abstract	p. 15
References	p. 16
Summary	p. 29
References	p. 30
Abstract	p. 33
Recurrent Attractor Neural Networks in Models of Cortical Associative Memory Function	p. 33
A Biophysically-Based Model of the Neostriatum as A Dynamically Reconfigurable Network	p. 43
Introduction	p. 44
References	p. 54
Dynamical Approximation by Neural Nets	p. 57
Introduction	p. 58
References	p. 66
On Parallel Selective Principal Component Analysis	p. 67
Introduction	p. 68
Conclusions	p. 74
Efficient Neural Net Isomorphism Testing	p. 77
Introduction	p. 78
References	p. 85
The Teco Theory - Simulation of Recognition Failure	p. 87
Introduction	p. 89
Conclusion	p. 98
References	p. 100
Searching Weight Space for Backpropagation Solution Types	p. 103
Introduction	p. 104
Conclusions	p. 117
References	p. 119
Features of Distributed Representations for Tree-Structures: A Study of Raam	p. 121
I Introduction	p. 122
Conclusions	p. 134
References	p. 136
Appendix: 1 Hierarchical Cluster Analysis Diagrams	p. 137
Appendix: 2	p. 138
Appendix: 3	p. 139
Using the Conceptual Graph Model as Intermediate Representation for Knowledge Translation in Hybrid Systems	p. 141
Introduction	p. 142
Conclusions	p. 151
References	p. 152
Adaptive Generalization in Dynamic Neural Networks	p. 153
Introduction	p. 154
References	p. 164
Diversity, Neural Nets and Safety Critical Applications*	p. 165
Introduction	p. 166
Conclusions	p. 175
References	p. 177
Some Experiments Using Extra Output Learning to Hint Multi Layer Perceptrons	p. 179
Introduction	p. 180
Conclusion	p. 188
References	p. 190
Minimization of Quantization Errors in Digital Implementations of Multi Layer Perceptrons	p. 191
Introduction	p. 192
Conclusion	p. 201
Acknowledgements	p. 201
References	p. 202
Multimodal Sensing for Motor Control	p. 203
Introduction	p. 204
Conclusion	p. 215
References	p. 216
Modeling, Connectionist and Otherwise	p. 217
Introduction	p. 218
References	p. 235
A Connectionist Exploration of the Computational Implications of Embodiment	p. 237
Introduction	p. 238
Conclusions	p. 254
Conclusions	p. 255
Behaviorism and Reinforcement Learning	p. 259
Introduction	p. 260
References	p. 270
Symbol Grounding and Transcendental Logic	p. 271
Conclusions	p. 281
Acknowledgements	p. 281
References	p. 282
Connectionist Synthetic Epistemology: Requirements for the Development of Objectivity	p. 283
Abstract	p. 283
Acknowledgements	p. 308
References	p. 309
Are Representations Still Necessary for Understanding Cognition?	p. 311
Introduction	p. 312
Conclusion	p. 319
Indeterminacy and Experience	p. 321
Abstract	p. 321
References	p. 328
The Symbolic-Subsymbolic Relation: from Limitivism to Correspondence	p. 331
Introduction	p. 331
References	p. 343
Learning to Retrieve Information	p. 345
Introduction	p. 346
Summary	p. 352
Acknowledgements	p. 353
Connectionist Models for the Detection of Oil Spills from Doppler Radar Imagery	p. 355
Introduction	p. 356
References	p. 370
The Neural Network House: an Overview	p. 371
Introduction	p. 372
Acknowledgements	p. 379
Author Index	p. 381
Table of Contents provided by Publisher. All Rights Reserved.

What is included with this book?

The New copy of this book will include any supplemental materials advertised. Please check the title of the book to determine if it should include any access cards, study guides, lab manuals, CDs, etc.

The Used, Rental and eBook copies of this book are not guaranteed to include any supplemental materials. Typically, only the book itself is included. This is true even if the title states it includes any access cards, study guides, lab manuals, CDs, etc.

FREE SHIPPING

Amazon no longer offers textbook rentals. We do!

Current Trends in Connectionism: Proceedings of the 1995 Swedish Conference on Connectionism

Summary

Table of Contents

Supplemental Materials