A "neural" network model that supports realtime learning of temporal relationships in complex engineering domains
Author:
Open Access
- 1 September 1992
- journal article
- other
- Published by SAGE Publications in SIMULATION
- Vol. 59 (3) , 152-163
Abstract
Difficulties in developing, maintaining, and validating knowledge base have motivated an increasing interest in adaptive systems. However, the symbolic paradigm has proven resistant to learning in environ ments that are dynamic or noisy. This report documents a simulation-based research program that demonstrates the utility of a modified connectionist memory unit as the basis for a robust reinforcement model that learns in such environments. This learning model generates effective rule- based behavior from a qualitative, goal-based architecture that further supports the development of secondary goals, or mental models, derived from experiences in these complex domains.Keywords
This publication has 9 references indexed in Scilit:
- A theory of the origins of human knowledgeArtificial Intelligence, 1989
- Introduction:Paradigms for machine learningArtificial Intelligence, 1989
- The scope and limitations of first generation expert systemsFuture Generation Computer Systems, 1987
- Parallel Distributed Processing1986
- How many memory systems are there?American Psychologist, 1985
- Categorization and Representation of Physics Problems by Experts and Novices*Cognitive Science, 1981
- Toward a modern theory of adaptive networks: Expectation and prediction.Psychological Review, 1981
- Physical Symbol Systems*Cognitive Science, 1980
- Perception in chessCognitive Psychology, 1973