Communicating neural network knowledge between agents in a simulated aerial reconnaissance system [1 citations — 0 self]

Download:

by Stephen Quirolgico, Kip Canfield, Timothy Finin, James A. Smith

Proc. of the First Interl. Symposium on Agent Systems and Applications – Third Interl. Symposium on Mobile Agents

http://www.cs.umbc.edu/~squiro1/papers/asa99.ps.gz

Add To MetaCart

Popular Tags

No tags have been applied to this document.

BibTeX | Add To MetaCart

@INPROCEEDINGS{Quirolgico_communicatingneural,
    author = {Stephen Quirolgico and Kip Canfield and Timothy Finin and James A. Smith},
    title = {Communicating neural network knowledge between agents in a simulated aerial reconnaissance system},
    booktitle = {Proc. of the First Interl. Symposium on Agent Systems and Applications – Third Interl. Symposium on Mobile Agents},
    year = {}
}

Abstract:

In order to maintain their performance in a dynamic environment, agents may be required to modify their learning behavior during run-time. If an agent utilizes a rule-based system for learning, new rules may be easily communicated to the agent in order to modify the way in which it learns. However, if an agent utilizes a connectionist-based system for learning, the way in which the agent learns typically remains static. This is due, in part, to a lack of research in communicating subsymbolic information between agents. In this paper, we present a framework for communicating neural network knowledge between agents in order to modify an agent's learning and pattern classification behavior. This framework is applied to a simulated aerial reconnaissance system in order to show how the communication of neural network knowledge can help maintain the performance of agents tasked with recognizing images of mobile military objects. 1.

Citations

887	Reinforcement learning: A survey – Kaelbling, Littman, et al. - 1996
861	KQML as an Agent Communication Language – Finin, Fritzson, et al. - 1994
334	Knowledge interchange format, version 3.0 reference manual – Genesereth, Fikes - 1992
240	Software agents: An overview – Nwana - 1996
239	Escaping brittleness: the possibilities of generalpurpose learning algorithms applied to parallel rule-based systems – Holland - 1986
170	Extracting refined rules from knowledge-based neural networks – Towell, Shavlik - 1993
151	Modelling adaptive autonomous agents – Maes - 1995
115	A proposal for a new KQML specification – Labrou, Finin - 1997
103	Reinforcement learning in the multi-robot domain – Matarić - 1997
97	JAM: Java agents for meta-learning over distributed databases – Stolfo, Prodromidis, et al. - 1997
76	Learning from hints in neural networks – Abu-Mostafa - 1990
44	Cooperative case-based reasoning – Plaza, Arcos, et al.
24	Experiments on the transfer of knowledge between neural networks – Pratt - 1994
20	Transferring Previously Learned Back-Propagation Neural Networks to New Learning Tasks – Pratt - 1993
19	Jackal: A JavaBased Tool for Agent Development – Cost, Labrou, et al.
8	Neural Network Toolbox, User’s Guide, Version 4. The MathWorks – Demuth, Beale - 2004
8	Neural network classification and formalization – Fiesler - 1994
3	Algorithms for pattern classification – Kashyap - 1970
2	Communication as the basis for learning in multi-agent systems – Kaiser, Dillman, et al. - 1996
1	Adaptation and learning in multi-agent systems: Some remarks and a bibliography – Weiβ - 1996
1	Adaptation and learning in multi-agent systems: Some remarks and a bibliography – Weib - 1996

View or Download | Add to My Collection | Correct Errors