Ebook: 4th Neural Computation and Psychology Workshop, London, 9–11 April 1997: Connectionist Representations

This volume collects together refereed versions of twenty-five papers presented at the 4th Neural Computation and Psychology Workshop, held at University College London in April 1997. The "NCPW" workshop series is now well established as a lively forum which brings together researchers from such diverse disciplines as artificial intelligence, mathematics, cognitive science, computer science, neurobiology, philosophy and psychology to discuss their work on connectionist modelling in psychology. The general theme of this fourth workshop in the series was "Connectionist Repre­ sentations", a topic which not only attracted participants from all these fields, but from allover the world as well. From the point of view of the conference organisers focusing on representational issues had the advantage that it immediately involved researchers from all branches of neural computation. Being so central both to psychology and to connectionist modelling, it is one area about which everyone in the field has their own strong views, and the diversity and quality of the presentations and, just as importantly, the discussion which followed them, certainly attested to this.

---

This volume contains a collection of papers presented at the 4th Neural Computation and Psychology Workshop, held in London from 7-11 April 1997. The theme of the workshop was: Connectionist Representations: Theory and Practice which covers many importan t issues ranging from the philosophical (such as the grounding problem), and the physiological (what can connectionist representations tell us about the real neural system?), to the technical (what is needed in order to get specific models to work?). The topic is one of increasing importance within Neural Computing and covers issues of interest to researchers from a wide range of backgrounds including: artificial intelligence, applied mathematics, cognitive science, computer science, neurobiology, phi losophy and psychology. In providing a comprehensive overview of this topic it provides an invaluable contribution to the Perspectives in Neural Computing series.

---

This volume contains a collection of papers presented at the 4th Neural Computation and Psychology Workshop, held in London from 7-11 April 1997. The theme of the workshop was: Connectionist Representations: Theory and Practice which covers many importan t issues ranging from the philosophical (such as the grounding problem), and the physiological (what can connectionist representations tell us about the real neural system?), to the technical (what is needed in order to get specific models to work?). The topic is one of increasing importance within Neural Computing and covers issues of interest to researchers from a wide range of backgrounds including: artificial intelligence, applied mathematics, cognitive science, computer science, neurobiology, phi losophy and psychology. In providing a comprehensive overview of this topic it provides an invaluable contribution to the Perspectives in Neural Computing series.
Content:
Front Matter....Pages i-xiii
Front Matter....Pages 1-1
Some Advantages of Localist over Distributed Representations....Pages 3-15
Distributed Representations in Radial Basis Function Networks....Pages 16-25
A unified framework for connectionist models....Pages 26-39
Separability is a Learner’s Best Friend....Pages 40-46
A Generative Learning Algorithm that uses Structural Knowledge of the Input Domain yields a better Multi-layer Perceptron....Pages 47-57
Improving Learning and Generalization in Neural Networks through the Acquisition of Multiple Related Functions....Pages 58-70
Front Matter....Pages 71-71
Objective Functions for Topography: A Comparison of Optimal Maps....Pages 73-83
Testing Principal Component Representations for Faces....Pages 84-97
Selection for Object Identification: Modelling Emergent Attentional Processes in Normality and Pathology....Pages 98-112
Extracting Features from the Short-term Time Structure of Cochlear Filtered Sound....Pages 113-125
Front Matter....Pages 127-127
Representational Issues in Neural Systems: Example from a Neural Network Model of Set-Shifting Paradigm Experiments....Pages 129-141
Models of Coupled Anterior Working Memories for Frontal Tasks....Pages 142-154
A Neurobiologically Inspired Model of Working Memory Based on Neuronal Synchrony and Rythmicity....Pages 155-167
Neural Networks and the Emergence of Consciousness....Pages 168-182
Selective memory loss in aphasics: An insight from pseudo-recurrent connectionist networks....Pages 183-195
Front Matter....Pages 197-197
Extracting Semantic Representations from Large Text Corpora....Pages 199-212
Modelling Lexical Decision Using Corpus Derived Semantic Representations in a Connectionist Network....Pages 213-226
Semantic Representation and Priming in a Self-organizing Lexicon....Pages 227-239
Distributed representations and the bilingual lexicon: One store or two?....Pages 240-253
Recognising Embedded Words in Connected Speech: Context and Competition....Pages 254-266
Front Matter....Pages 267-267
Dynamic Representation of Structural Constraints in Models of Serial Behaviour....Pages 269-282
Representations of Serial Order....Pages 283-300
To Repeat or Not to Repeat: The Time Course of Response Suppression in Sequential Behaviour....Pages 301-315
A Localist Implementation of the Primacy Model of Immediate Serial Recall....Pages 316-330
Connectionist Symbol Processing with Causal Representations....Pages 331-342
Back Matter....Pages 343-343

---

This volume contains a collection of papers presented at the 4th Neural Computation and Psychology Workshop, held in London from 7-11 April 1997. The theme of the workshop was: Connectionist Representations: Theory and Practice which covers many importan t issues ranging from the philosophical (such as the grounding problem), and the physiological (what can connectionist representations tell us about the real neural system?), to the technical (what is needed in order to get specific models to work?). The topic is one of increasing importance within Neural Computing and covers issues of interest to researchers from a wide range of backgrounds including: artificial intelligence, applied mathematics, cognitive science, computer science, neurobiology, phi losophy and psychology. In providing a comprehensive overview of this topic it provides an invaluable contribution to the Perspectives in Neural Computing series.
Content:
Front Matter....Pages i-xiii
Front Matter....Pages 1-1
Some Advantages of Localist over Distributed Representations....Pages 3-15
Distributed Representations in Radial Basis Function Networks....Pages 16-25
A unified framework for connectionist models....Pages 26-39
Separability is a Learner’s Best Friend....Pages 40-46
A Generative Learning Algorithm that uses Structural Knowledge of the Input Domain yields a better Multi-layer Perceptron....Pages 47-57
Improving Learning and Generalization in Neural Networks through the Acquisition of Multiple Related Functions....Pages 58-70
Front Matter....Pages 71-71
Objective Functions for Topography: A Comparison of Optimal Maps....Pages 73-83
Testing Principal Component Representations for Faces....Pages 84-97
Selection for Object Identification: Modelling Emergent Attentional Processes in Normality and Pathology....Pages 98-112
Extracting Features from the Short-term Time Structure of Cochlear Filtered Sound....Pages 113-125
Front Matter....Pages 127-127
Representational Issues in Neural Systems: Example from a Neural Network Model of Set-Shifting Paradigm Experiments....Pages 129-141
Models of Coupled Anterior Working Memories for Frontal Tasks....Pages 142-154
A Neurobiologically Inspired Model of Working Memory Based on Neuronal Synchrony and Rythmicity....Pages 155-167
Neural Networks and the Emergence of Consciousness....Pages 168-182
Selective memory loss in aphasics: An insight from pseudo-recurrent connectionist networks....Pages 183-195
Front Matter....Pages 197-197
Extracting Semantic Representations from Large Text Corpora....Pages 199-212
Modelling Lexical Decision Using Corpus Derived Semantic Representations in a Connectionist Network....Pages 213-226
Semantic Representation and Priming in a Self-organizing Lexicon....Pages 227-239
Distributed representations and the bilingual lexicon: One store or two?....Pages 240-253
Recognising Embedded Words in Connected Speech: Context and Competition....Pages 254-266
Front Matter....Pages 267-267
Dynamic Representation of Structural Constraints in Models of Serial Behaviour....Pages 269-282
Representations of Serial Order....Pages 283-300
To Repeat or Not to Repeat: The Time Course of Response Suppression in Sequential Behaviour....Pages 301-315
A Localist Implementation of the Primacy Model of Immediate Serial Recall....Pages 316-330
Connectionist Symbol Processing with Causal Representations....Pages 331-342
Back Matter....Pages 343-343
....