From associations to rules : connectionist models of behavior and cognition : proceedings of the tenth Neural Computation and Psychology Workshop, Dijon, France, 12-14 April 2007 /
This book introduces a host of connectionist models of cognition and behavior. The major areas covered are high-level cognition, language, categorization and visual perception, and sensory and attentional processing. All of the articles cover unpublished research work. The key contribution of this b...
Clasificación: | Libro Electrónico |
---|---|
Autor Corporativo: | |
Otros Autores: | , |
Formato: | Electrónico Congresos, conferencias eBook |
Idioma: | Inglés |
Publicado: |
Hackensack, N.J. :
World Scientific,
©2008.
|
Colección: | Progress in neural processing ;
17. |
Temas: | |
Acceso en línea: | Texto completo |
Tabla de Contenidos:
- Introduction; CONTENTS; Section I High-Level Cognition; A Connectionist Approach to Modelling the Flexible Control of Routine Activities Nicolas Ruh, Richard P. Cooper and Denis Mareschal; 1. Introduction; 2. Existing Models of Sequential Control; 3. The Goal Circuit Model; 3.1. Goal Units and Simulated Reinforcement Learning; 3.2. Progressive Routinisation; 3.3. Network Architecture and Parameters; 4. Results; 4.1. The Coffee or Tea Routine; 4.2. Redundancy and Goal Directed Behaviour; 4.3. Deliberate Control; 5. Discussion; References.
- Associative and Connectionist Accounts of Biased Contingency Detection in Humans Serban C. Musca, Miguel A. Vadillo, Fernando Blanco and Helena Matute1. Introduction; 1.1. Studies of Contingency Judgment; 1.2. Illusory Correlation; 2. Outcome-density Effect; 2.1. An Associative Account: The Rescorla-Wagner Model; 2.2. Connectionist Simulations: What is the Minimal Model?; 2.2.1. Translating the Problem into "Neural Networks Language"; 2.2.2. Three-layer Hetero-associative Network; 2.2.3. Three-layer Auto-hetero-associative Network; 3. Conclusion; References.
- On the Origin of False Memories: At Encoding or at Retrieval?
- A Contextual Retrieval Analysis Eddy J. Davelaar1. Introduction; 2. The Deese/Roediger-McDermott paradigm; 2.1. Theoretical accounts of false memories; 2.2. DRM findings related to encoding/retrieval; 3. Contextual retrieval; 3.1. Context models; 3.2. Contextual retrieval analysis; 4. Experiments; 4.1. Experimental method; 4.2. Results; 4.3. Interpretation; 4.4. Methodological considerations; 5. Discussion; Acknowledgments; References; Another Reason Why We Should Look After Our Children John A. Bullinaria; 1. Introduction.
- 2. Evolving Neural Network Systems3. Simulation Results for Different Protection Periods; 4. Allowing the Protection Period to Evolve; 5. Analysis of the Evolved Performance; 6. Discussion and Conclusions; References; Section II Language; A Multimodal Model of Early Child Language Acquisition Abel Nyamapfene; 1. Introduction; 2. Overview of Child Language at the One-Word and Two-Word Stages; 3. Simulating One-Word Child Language; 3.1. The Modified Counterpropagation Network; 3.2. One-Word Stage Model Simulation; 4. Simulating the Transition form One-Word to Two Word Language.
- 4.1. Temporal Hypermap Model for Two-word Simulation4.2. A Gated Multi-net Architecture for One-Word to Two-Word Transition -; 4.3. Gated Multinet Model Simulation; 5. Conclusion and Future work; References; Constraints on Generalisation in a Self-Organising Model of Early Word Learning Julien Mayor and Kim Plunkett; 1. Introduction; 2. Method; 2.1. Training the Unimodal Maps; 2.2. Coding the inputs; 2.2.1. Image generation; 2.2.2. On the importance of real acoustic token; 2.3. Forming the cross-modal associations; 3. Results; 3.1. Generalisation as a function of number of pairings.