To learn or not to learn ......

  • Anupam Joshi
Workshop Contributions
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1042)


Multiagent systems in which agents interact with each other are now being proposed as a solution to many problems which can be grouped together under the “distributed problem solving” umbrella. For such systems to work properly, it is necessary that agents learn from their environment and adapt their behaviour accordingly. In this paper we present a system which uses a combination of neuro-fuzzy learning and static adaptation to coordinate the activity of multiple agents. An epistemic utility based formulation is used to automatically generate the exemplars for learning, making the process unsupervised. The system has been developed in the context of a scientific computing scenario.


Multi Agent System Multiagent System Scientific Computing Hardware Platform Acceptance System 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    T. Drashansky, A. Joshi, and J.R. Rice. SciAgents — An Agent Based Environment for Distributed, Cooperative Scientific Computing. Technical Report TR-95-029, Dept. Comp. Sci., Purdue University, 1995. (submitted to Tools with AI '95).Google Scholar
  2. 2.
    E. Gallopoulos, E. Houstis, and J.R. Rice. Computer as Thinker/Doer: Problem-Solving Environments for Computational Science. IEEE Computational Science and Enginerring, 1(2):11–23, 1994.Google Scholar
  3. 3.
    A. Joshi, T. Drashansky, E. Houstis, and S. Weerawarana. SciencePad: An Intelligent Electronic Notepad for Ubiquitous Scientific Computing. In International Conference on Inteligent Information Management Systems, June 1995. (to appear).Google Scholar
  4. 4.
    S. Weerawarana et al. Using NCSA Mosaic to build notebook interfaces for CS&E applications. Technical Report CSD-TR-95-006, Department of Computer Sciences, Purdue University, 1995. (submitted to IFIP WG2.7 EHCI '95).Google Scholar
  5. 5.
    E. Houstis et al. The PYTHIA projet. In Proc. First Intl. Conf. on Neural, Parallel and Scientific Computing, 1995. (to appear).Google Scholar
  6. 6.
    S. Weerawarana. Problem Solving Environments for Partial Differential Equation Based Systems. PhD thesis, Dept. Comp. Sci., Purdue University, 1994.Google Scholar
  7. 7.
    A. Joshi et al. The Use of Neural Networks to Support Intelligent Scientific Computing. In Proc. IEEE Intl. Conf. Neural Networks. IEEE, IEEE Press, July 1995.Google Scholar
  8. 8.
    N. Ramakrishnan et al. Neuro-Fuzzy Systems for Intelligent Scientific Computing. Technical Report TR-95-026, Dept. Comp. Sci., Purdue University, 1995.Google Scholar
  9. 9.
    P.K. Simpson. Fuzzy min-max neural networks-part I: Classification. IEEE Trans. Neural Networks, 3:776–786, Sept 1992.Google Scholar
  10. 10.
    P.K. Simpson. Fuzzy min-max neural networks-part II: Clustering. IEEE Trans. Fuzzy Systems, 1(1):32–45, Feb 1993.Google Scholar
  11. 11.
    S. Newton and S. Mitra. Self organizing leader clustering in a neural network using a fuzzy learning rule. In SPIE Proc. 1565: adaptive signal processing. SPIE, 1991.Google Scholar
  12. 12.
    G. Carpenter, S. Grossberg, and S. Rosen. Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system. Neural Networks, 4:759–771, 1991.Google Scholar
  13. 13.
    A. Joshi, S. Weerawarana, N. Ramakrishnan, E.N. Houstis, and J.R. Rice. Neural and Neuro-Fuzzy Approaches to Support ”Intelligent” Scientific Problem Solving. Technical Report TR-95-039, Dept. Comp. Sci., Purdue University, 1995.Google Scholar
  14. 14.
    H. Braun and M. Riedmiller. Rprop: A Fast and Robust Backpropagation Learning Strategy. In Proceedings of the ACNN, 1993.Google Scholar
  15. 15.
    Y. Lashkari, M. Metral, and P. Maes. Collaborative Interface Agents. In Proceedings AAAI '94. AAAI, 1994.Google Scholar
  16. 16.
    K. Lehrer. Theory of Knowledge. Westview Press, Boulder, CO, USA, 1990.Google Scholar
  17. 17.
    I. Levi. Decisions and Revisions. Cambridge University Press, Cambridge, U.K., 1984.Google Scholar
  18. 18.
    J. Neyman and E.S. Pearson. The Testing of Statistical Hypotheses in Relations to Probabilities a priori. Proc. Cambridge Phil. Soc., 29:492–510, 1932.Google Scholar
  19. 19.
    J. Neyman. Basic Ideas and Some Recent Results of the Thoery of Testing Statistical Hypotheses. J. Royal Stat. Soc., 105:292–327, 1942.Google Scholar
  20. 20.
    I. Levi. The Enterprise of Knowledge. The MIT Press, CAmbridge, MA, USA, 1980.Google Scholar
  21. 21.
    W.C. Stirling. Coordinated Intelligent Control via Epistemic Utiliyu Theory. IEEE Control Systems, pages 21–29, October 1993.Google Scholar
  22. 22.
    W.C. Stirling and D.R. Morrell. Convex Bayes Decision Theory. IEEE Trans. System, Man and Cybernetics, 21:173–183, 1991.Google Scholar
  23. 23.
    D. Marinescu and J.R. Rice. On the scalability of Asynchronous Parallel Computations. J. Parallel and Distributed Computing, 22, 1994.Google Scholar
  24. 24.
    E. Mascarenhas and V. Rego. Ariadne: Architecture of a Portable Threads System Supporting Mobile Processes. Technical Report CSD-TR-95-017, Dept. Comp. Sci., Purdue University, 1995.Google Scholar
  25. 25.
    V. Rego et al. Process Mobility in Distributed Memory Simulation Systems. In Proc. Winter Simulation Conference, pages 722–730, 1993.Google Scholar
  26. 26.
    R. Fritzson et. al. KQML — A Language and Protocol for Knowledge and Information Exchange. In Proc. 13th Intl. Distributed Artificial Intelligence Workshop, July 1994.Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1996

Authors and Affiliations

  • Anupam Joshi
    • 1
  1. 1.Department of Computer SciencesPurdue UniversityWest LafayetteUSA

Personalised recommendations