Cargando…
Connectionist models : proceedings of the 1990 summer school /
| Clasificación: | Libro Electrónico |
|---|---|
| Autor Corporativo: | |
| Otros Autores: | |
| Formato: | Electrónico Congresos, conferencias eBook |
| Idioma: | Inglés |
| Publicado: |
San Mateo, Calif. :
M. Kaufmann Publishers,
�1991.
|
| Temas: | |
| Acceso en línea: | Texto completo |
Tabla de Contenidos:
- Front Cover; Connectionist Models; Copyright Page; Table of Contents; Foreword; Participants in the 1990 Connectionist Models Summer School; List Of Accepted Students; Part I: Mean Field, Boltzmann, and Hopfield Networks; Chapter 1. Deterministic Boltzmann Learning in Networks with Asymmetric Connectivity; Abstract; 1 INTRODUCTION; 2 DETERMINISTIC BOLTZMANN LEARNING IN SYMMETRIC NETWORKS; 3 ASYMMETRIC NETWORKS; 4 SIMULATION RESULTS; 5 DISCUSSION; Acknowledgement; References; APPENDIX; Chapter 2. Contrastive Hebbian Learning in the Continuous Hopfield Model; Abstract; 1 INTRODUCTION.
- 2 STABILITY OF ACTIVATIONS3 CONTRASTIVE LEARNING; 4 DISCUSSION; 5 APPENDIX; Acknowledgements; References; Chapter 3. Mean field networks that learn to discriminate temporally distorted strings; Abstract; INTRODUCTION; PREVIOUS APPROACHES USING NEURAL NETS; THE LEARNING PROCEDURE FOR THE MEAN FIELD MODULES; THE TASK USED IN THE SIMULATIONS; RESULTS AND DISCUSSION; Acknowledgements; References; Chapter 4. Energy Minimization and the Satisfiability of Propositional Logic; Abstract; 1 Introduction; 2 Satisfiability and models of propositional formulas; 3 Equivalence between WFFs.
- 4 Conversion of a WFF into Conjunction of Triples Form (CTF)5 Energy functions; 6 The equivalence between high order models and low order models; 7 Describing WFFs by energy functions; 8 The penalty function; 9 Mapping from a satisfiability problem to a minimization problem and vice versa; 10 Summary, applications and conclusions; Acknowledgments; References; Part II: Reinforcement Learning; Chapter 5. On the Computational Economics of Reinforcement Learning; Abstract; 1 INTRODUCTION; 2 INDIRECT AND DIRECT ADAPTIVE CONTROL; 3 MARKOV DECISION PROBLEMS.
- 4 INDIRECT AND DIRECT LEARNING FOR MARKOV DECISION PROBLEMS5 AN INDIRECT ALGORITHM; 6 Q-LEARNING; 7 SIMULATION RESULTS; 8 DISCUSSION; 9 CONCLUSION; Acknowledgements; References; Chapter 6. Reinforcement Comparison; Abstract; 1 INTRODUCTION; 2 THEORY; 3 RESULTS; 4 CONCLUSIONS; Acknowledgements; References; Chapter 7. Learning Algorithms for Networks with Internal and External Feedback; Abstract; 1 Terminology; 2 The Neural Bucket Brigade Algorithm; 3 A Reinforcement Comparison Algorithm for Continually Running Fully Recurrent Probabilistic Networks.
- 4 Two Interacting Fully Recurrent Self-Supervised Learning Networks for Reinforcement Learning5 An Example for Learning Dynamic Selective Attention: Adaptive Focus Trajectories for Attentive Vision; 6 An Adaptive Subgoal Generator for Planning Action Sequences; References; Part III: Genetic Learning; Chapter 8. Exploring Adaptive Agency I: Theory and Methods for Simulating the Evolution of Learning; Abstract; 1 INTRODUCTION; 2 NATURAL SELECTION AND THE EVOLUTION OF SUBSIDIARY ADAPTIVE PROCESSES; 3 A BRIEF HISTORY OF LEARNING THEORY IN (COMPARATIVE) PSYCHOLOGY.