Abstract
To accomplish the autonomous behavior of agents, several top-down and bottom-up agent learning architectures that consist of procedural and declarative knowledge have been implemented. They use mechanisms such as production rules, supervised neural networks and unsupervised neural networks to declare procedural knowledge. An efficient representation of procedural knowledge enhances learning and decision making. Inspired by the representation of rules, facts and knowledge in human memory, this paper presents a novel cognitive memory model, Episodic Associative Memory with a Neighborhood Effect (EAMwNE) as a method to define procedural knowledge.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Sun, R., Merrill, E., Peterson, T.: From implicit skills to explicit knowledge: a bottomup model of skill learning. Cognitive Science 25(2), 203–244 (2001)
Graca, P.R., Gaspar, G.: Using Cognition and Learning to Improve Agents’ Reactions. In: Adaptive Agents and Multi-Agent Systems, Springer, Heidelberg (2003)
Sun, R.: An agent architecture for on-line learning of procedural and declarative knowledge. In: ICONIP 1997, Springer, Heidelberg (1997)
Sun, R., Bookman, L. (eds.): Computational Architectures Integrating Neural and Symbolic Processes. Kluwer Academic Publishers, Norwell (1994)
Wickramasinghe, L.K., Alahakoon, L.D.: Adaptive Agent Architecture Inspired by Human Behavior. In: IEEE/WIC International Conference on Intelligent Agent Technology IAT 2004, IEEE Computer Society, Beijing (2004)
Miikkulainen, R.: Trace feature map: A model of episodic associative memory. Biological Cybernetics 67, 273–282 (1992)
Anderson, J.R.: Rules of the Mind. Lawrence Erlbaum Associates, Hillsdale (1993)
Alahakoon, L.D., Halgamuge, S.K., Sirinivasan, B.: Dynamic Self Organizing Maps with Controlled Growth for Knowledge Discovery. IEEE Transactions on Neural Networks, Special Issue on Knowledge Discovery and Data Mining 11(3), 601–614 (2000)
Moll, M., Miikkulainen, R.: Convergence-Zone Episodic Memory: Analysis And Simulations. Neural Networks 10, 1017–1036 (1997)
Wickramasinghe, L.K., Alahakoon, L.D.: Enhancing Agent Autonomy and Adaptive Behavior by Knowledge Abstraction. In: The second International Conference on Autonomous Robots and Agents (ICARA 2004), Massey University, Palmerston North (2004)
Hintzman, D.L.: Schema Abstraction in a Multiple-Trace Memory Model. Psychological Review 93(4), 411–428 (1986)
Klingspor, V., Morik, K.J., Rieger, A.D.: Learning Concepts from Sensor Data of a Mobile Robot. Machine Learning 23, 305–332 (1996)
Sun, R., Peterson, T., Merrill, E.: A Hybrid Architecture for Situated Learning of Reactive Sequential Decision Making. Applied Intelligence 11(1), 109–127 (1999)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2005 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Wickramasinghe, K., Alahakoon, D. (2005). Representation of Procedural Knowledge of an Intelligent Agent Using a Novel Cognitive Memory Model. In: Khosla, R., Howlett, R.J., Jain, L.C. (eds) Knowledge-Based Intelligent Information and Engineering Systems. KES 2005. Lecture Notes in Computer Science(), vol 3681. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11552413_102
Download citation
DOI: https://doi.org/10.1007/11552413_102
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-28894-7
Online ISBN: 978-3-540-31983-2
eBook Packages: Computer ScienceComputer Science (R0)