Current Trends in Connectionism: Proceedings of the Swedish Conference on Connectionism, 1995Lars F. Niklasson, Mikael B. Bodén Psychology Press, 1995 - 382 páginas 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. |
Índice
Redish A David | 1 |
Physiological Constraints on Models of Behavior | 15 |
Erik Fransén Anders Lansner | 33 |
A BiophysicallyBased Model of the Neostriatum as Dynami | 43 |
Dynamical Approximation by Neural Nets | 57 |
On Parallel Selective Principal Component Analysis | 67 |
Efficient Neural Net Isomorphism Testing | 77 |
The TECO Theory Simulation of Recognition Failure | 87 |
Some Experiments Using Extra Output Learning to Hint | 179 |
Minimization of Quantization Errors in Digital Implementa | 191 |
Modeling Connectionist and Otherwise | 217 |
A Connectionist Exploration of the Computational Implica | 237 |
Behaviorism and Reinforcement Learning | 259 |
Requirements for | 283 |
Are Representations Still Necessary for Understanding Cog | 311 |
From Limitivism | 331 |
Searching Weight Space for Backpropagation Solution Types | 103 |
Using the Conceptual Graph Model as Intermediate Repre | 141 |
Adaptive Generalization in Dynamic Neural Networks | 153 |
Diversity Neural Nets and Safety Critical Applications | 165 |
Learning to Retrieve Information | 345 |
Vidmar Lucky 371 | 355 |
An Overview | 371 |
Otras ediciones - Ver todo
Current Trends in Connectionism: Proceedings of the 1995 Swedish Conference ... Lars F. Niklasson,Mikael B. Bod‚n Vista previa restringida - 2013 |
Current Trends in Connectionism: Proceedings of the 1995 Swedish Conference ... Lars F. Niklasson,Mikael B. Bod‚n Vista previa restringida - 2013 |
Términos y frases comunes
abstract acetylcholine activity algorithm analysis approximation Artificial Neural Networks attractor backpropagation basal ganglia behavior binary brain classification clipping cognitive science computational concept Conference on Connectionism Connectionism connectionist models connections constituents context correlation correspondence cortex cortical described developed distribution domain dopamine dynamical systems environment error example experiments feed-forward Figure Fransén functional equivalence Hasselmo hidden layer hidden unit vectors hint hippocampal implemented interaction landmarks language Lansner learning location codes method methodologies MLPs motor neostriatum neural net neural nets neural network neurons nodes oil spill optimization output weight vector parameters performance predictions problem pyramidal cells Quadrant queries RAAM recall recognition recurrent region relevant represent representation resolution cells retrieval sensory sensory-motor sequence Sharkey simulations Smolensky solution types space spatial SRN's structure superior colliculus Swedish Conference Symbol Grounding synaptic synesthesia systematicity target task TECO tion training set values visual weight space Wmax