Advertisement

ECOS — Evolving Connectionist Systems — a New/Old Paradigm for On-line Learning and Knowledge Engineering

  • Nikola Kasabov
Part of the Studies in Fuzziness and Soft Computing book series (STUDFUZZ, volume 45)

Abstract

This chapter makes a revision of the major principles, applications and publications on the evolving connecionist systems (ECOS) paradigm. It compares ECOS with other AI models and outlines directions for further research.

Keywords

Evolving connectionist systems neural networks adaptive systems. 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

ECOS and EFuNN References

  1. 1.
    Abdulla, W. and N. Kasabov, Parallel CHMM speech recognition systems, Proc. of Joint Conference of Information Sciences (JCIS), Atlantic City, New Jersey, February 2000Google Scholar
  2. 2.
    Deng, D. and N. Kasabov, Evolving Self-orginizing Map and its Application in Generating a World Macroeconomic Map, In: Emerging Knowledge Engineering and Conectionist-based Systems (Proceedings of the ICONIP/AMZIIS/ANNES’99 Workshop “Future directions for intelligent systems and information sciences, Dunedin, 22–23 Nov.1999), N. Kasabov and K. Ko (eds), 7:12Google Scholar
  3. 3.
    Deng, D., I. Koprinska and N. Kasabov, RICBIS — New Zealand Repository for Intelligent Connectionist-Based Information Systems, In: Emerging Knowledge Engineering and Conectionist-based Systems (Proceedings of the ICONIP/AMZIIS/ANNES’99 Workshop “Future directions for intelligent systems and information sciences, Dunedin, 22–23 Nov.1999), N. Kasabov and K. Ko (eds), 182–185Google Scholar
  4. 4.
    Futschik, M; Schreiber, M; Brown, C, and Kasabov, N. (1999) “Comparative Studies of Neural Network Models for mRNA Analysis”, in Proc. Int. Conf. Intelligent Systems for Molecular biology, Heidelberg, August 6–10 (1999)Google Scholar
  5. 5.
    Ghobakhlou, A., Q. Song and N. Kasabov, ROKEL: The Interactive learning and Navigating Robot of the Knowledge Engineering laboratory at Otago, In: Emerging Knowledge Engineering and Connectionist-based Systems (Proceedings of the ICONIP/AMZIIS/ANNES’99 Workshop “Future directions for intelligent systems and information sciences, Dunedin, 22–23 Nov. 1999), N. Kasabov and K. Ko (eds) 57–59Google Scholar
  6. 6.
    Hegg, D., T. Cohen, N. Kasabov and Q. Song Intelligent Control of Sequencing Batch Reactors (SBRs) for Biological Nitrogen Removal, In: Emerging Knowledge Engineering and Conectionist-based Systems (Proceedings of the ICONIP/AMZIIS/ANNES’99 Workshop “Future directions for intelligent systems and information sciences, Dunedin, 22–23 Nov. 1999), N. Kasabov and K. Ko (eds), 152–155Google Scholar
  7. 7.
    Iliev, G. and N. Kasabov Adaptive Filtering with Averaging in Noise Cancellation for Voice and Speech Recognition, (Proceedings of the ICONIP/AMZIIS/ANNES’99 Workshop “Future directions for intelligent systems and information sciences, Dunedin, 22–23 Nov. 1999), N. Kasabov and K. Ko (eds) 71–75Google Scholar
  8. 8.
    Iliev, G., Kasabov, N. Adaptive noise cancellation for speech applications, Proc. of ICONIP’99, November 1999, Perth, Australia, IEEE Press (1999)Google Scholar
  9. 9.
    Iliev, G., Kasabov, N. Channel equalisation using adaptive filtering with averaging, in: Proc. of Joint Conference of Information Sciences (JCIS), Atlantic City, New Jersey, February 2000 (accepted)Google Scholar
  10. 10.
    Kasabov, N and B. Woodford, Rule insertion and rule extraction from evolving fuzzy neural networks: algorithms and applications for building adaptive, intelligent expert systems, 1999 IEEE International Fuzzy Systems Conference Proceedings, Seoul, August 1999, v.III, 1406–1409Google Scholar
  11. 11.
    Kasabov, N. and Fedrizzi, M. Fuzzy neural networks and evolving connectionist systems for intelligent decision making, Proceedings of the Eight International Fuzzy Systems Association World Congress, Taiwan, August 17–20 (1999)Google Scholar
  12. 12.
    Kasabov, N. and M. Watts. Spatial temporal evolving fuzzy neural networks and applications for adaptive phoneme recognition, IEEE Transactions on Neural Netwokrs, (1999) submitted, published as TR99–03, Department of Information Science, University of OtagoGoogle Scholar
  13. 13.
    Kasabov, N. and Q. Song. Dynamic “m-of-n” evolving fuzzy neural networks for online learning of dynamic time series, IEEE Transactions on Fuzzy Systems, (1999) submitted, published as TR99–04, Department of Information Science, University of OtagoGoogle Scholar
  14. 14.
    Kasabov, N. Brain-like functions in evolving connectionist systems for on-line, knowledge-based learning, in: T. Kitamura (ed) Modeling brain functions for intelligent systems, World Scientific (2000)Google Scholar
  15. 15.
    Kasabov, N. ECOS — A framework for evolving connectionist systems and the ‘eco’ training method, in: S. Usui and T. Omori (eds) Proceedings of ICONIPV8The Fifth International Conference on Neural Information Processing, Kitakyushu, Japan, 21–23 October 1998, IOS Press, vol.3, 1232–1235Google Scholar
  16. 16.
    Kasabov, N. Evolving connectionist and fuzzy connectionist systems — theory and applications for adaptive, on-line intelligent systems, In: Neuro-Fuzzy Techniques for Intelligent Information Systems, N. Kasabov and R.Kozma, eds. Heidelberg, Physica Verlag (1999) 111–146Google Scholar
  17. 17.
    Kasabov, N. Evolving connectionist and fuzzy connectionist systems for on-line adaptive decision making and control, in; Advances in Soft ComputingEngineering Design and Manufacturing, R. Roy, T. Furuhashi and P.K. Chawdhry (Eds.) Springer-Verlag, London Limited, 1999, 638 pagesGoogle Scholar
  18. 18.
    Kasabov, N. Evolving connectionist systems and applications for adaptive speech recognition, Proc. of IJCNN’99, Washington DC, July 1999, IEEE PressGoogle Scholar
  19. 19.
    Kasabov, N. Evolving connectionist systems for on-line, knowledge based learning. IEEE Transactions on Man, Systems and Cybernetics, (2000), published also as TR99–02, Department of Information Science, University of OtagoGoogle Scholar
  20. 20.
    Kasabov, N. Evolving fuzzy neural networks — algorithms, applications and biological motivation, in: T. Yamakawa and G. Matsumoto (eds) Methodologies for the Conception, Design and Application of Soft Computing, World Scientific, 1998, 271–274Google Scholar
  21. 21.
    Kasabov, N. Evolving fuzzy neural networks for adaptive, on-line intelligent agents and systems, in: O. Kaynak, S. Tosunoglu and M. Ang (eds) Recent Advances in Mechatronics, Springer Verlag , Singapore (1999): Proceedings of the international conference, Istanbul, Turkey, 24–26 May 1999, 27–41.Google Scholar
  22. 22.
    Kasabov, N. Evolving fuzzy neural networks: Theory and Applications for on-line adaptive prediction, decision making and control, Australian Journal of Intelligent Information Processing Systems, 5 (3): 154–160 (1998Google Scholar
  23. 23.
    Kasabov, N. On-line learning, reasoning, rule extraction and aggregation in locally optimised evolving fuzzy neural networks, Neurocomputing, (2000) in printGoogle Scholar
  24. 24.
    Kasabov, N. The ECOS framework and the ‘eco’ training method for evolving connectionist systems. Journal of Advanced Computational Intelligence (1998) vol.2, No.6, 195–202Google Scholar
  25. 25.
    Kasabov, N. Theory and applications of evolving connectionist agents and systems, Proceedings of the 1998 international conference on Neural Networks and Brain (NN&B), Beijing, October 27–30 (1998), Publishing House of Electronics Industry, China, 668–671Google Scholar
  26. 26.
    Kasabov, N., D. Tuck, and M. Watts, Implementing Knowledge and Data Fusion in a Versatile Software Environment for Adaptive Learning and Decision-Making, in: Proc. of the Int. Conference on Data Fusion, San Hose, July 1999 (1999)Google Scholar
  27. 27.
    Kasabov, N., D. Deng, L. Erzegovezi, M. Fedrizzi, A. Beber, D. Deng, Hybrid Intelligent Decision Support Systems and Applications for Risk Analysis and Prediction, International conference on intelligent systems for investment decision making, Bond University, Gold Cost, December (1999)Google Scholar
  28. 28.
    Kasabov, N., Israel, S., and B. Woodford. Hybrid evolving connectionist systems for image classification, Journal of Advanced Computational Intelligence (2000)Google Scholar
  29. 29.
    Kasabov, N., L. Erzegovezi, M. Fedrizzi, A. Beber, D. Deng, Hybrid Intelligent Decision Support Systems and Applications for Risk Analysis and Prediction of Evolving Economic Clusters in Europe, in the same volumeGoogle Scholar
  30. 30.
    Kasabov, N., S. Israel, B. Woodford, Methodology and evolving connectionist architecture for image pattern recognition, in: S. Pal, Ghosh and Kundu (eds,) Soft computing and image processing, Heidelberg, Physica-Verlag (Springer Verlag) (2000)Google Scholar
  31. 31.
    Koprinska, I. and N. Kasabov An Application of Evolving Fuzzy Neural Network for Compressed Video Parsing, In: Emerging Knowledge Engineering and Conectionist-based Systems (Proceedings of the ICONIP/AMZIIS/ANNES,99 Workshop “Future directions for intelligent systems and information sciences, Dunedin, 22–23 Nov. 1999), N. Kasabov and K. Ko (eds), 96–102Google Scholar
  32. 32.
    Swope, J.A., Kasabov, N., Williams, M., Neuro-fuzzy modelling of heart rate signals and applications to diagnostics, in: Szepanjuk ed, Fuzzy Systems in Medicine, Physica Verlag (2000) 519–542CrossRefGoogle Scholar
  33. 33.
    Taylor, J. and N. Kasabov Modelling the Emergence of Speech and Language through Evolving Connectionist Systems, in the same volumeGoogle Scholar
  34. 34.
    Taylor, J., N. Kasabov, and R. Kilgour, Modelling the Emergence of Speech Sopund Categories in Evolving Connectionist Systems, Proc. of the Joint Conference on Information Sciences, Atlantic City, 2000Google Scholar
  35. 35.
    Tuck, D., and Q. Song, Demonstration of an adaptive EFuNN application: an on-line robotic arm path planner, (Proceedings of the ICONIP/AMZIIS/ANNES’99 Workshop “Future directions for intelligent systems and information sciences, Dunedin, 22–23 Nov. 1999), N. Kasabov and K. Ko (eds),45–48Google Scholar
  36. 36.
    Tuck, D., M. Watts, Q. Song and N. Kasabov, A Practical and Flexible Environment for Adaptive Knowledge and Data Fusion Applications. In: Proc. of Int. Conf. On Applications of Intelligent Systems, Melbourne, Sept. 1999 (1999)Google Scholar
  37. 37.
    Watts, M., B. Woodford, N. Kasabov, FuzzyCOPE — A Software Environment for Building Intelligent Systems — the Past, the Present and the Future, In: Emerging Knowledge Engineering and Conectionist-based Systems (Proceedings of the ICONIP/AMZIIS/ANNES,99 Workshop “Future directions for intelligent systems and information sciences, Dunedin, 22–23 Nov. 1999), N. Kasabov and K. Ko (eds) 188–192Google Scholar
  38. 38.
    Woodford, B.J., N. Kasabov and H. Wearing, Fruit Image Analysis using Wavelets, In: Emerging Knowledge Engineering and Conectionist-based Systems (Proceedings of the ICONIP/AMZIIS/ANNES’99 Workshop “Future directions for intelligent systems and information sciences, Dunedin, 22–23 Nov. 1999), N. Kasabov and K. Ko (eds), 88–92Google Scholar

Related References

  1. 39.
    Blanzieri, E., P. Katenkamp, “Learning radial basis function networks on-line”, in: Proc. of Intern. Conf. On Machine Learning, 37–45 (1996)Google Scholar
  2. 40.
    Bottu and Vapnik, “Local learning computation”, Neural Computation, 4, 888–900 (1992)CrossRefGoogle Scholar
  3. 41.
    Edelman, G., Neuronal Darwinism: The theory of neuronal group selection, Basic Books (1992).Google Scholar
  4. 42.
    Freeman, J., D. Saad, “On-line learning in radial basis function networks”, Neural Computation vol. 9, No.7 (1997).Google Scholar
  5. 43.
    Fritzke, B. “A growing neural gas network learns topologies”, Advances in Neural In­formation Processing Systems, vol.7 (1995)Google Scholar
  6. 44.
    Gaussier, T., and S. Zrehen, “A topological neural map for on-line learning: Emergence of obstacle avoidance in a mobile robot”, In: From Animals to Animats No.3, 282–290, (1994).Google Scholar
  7. 45.
    Hech-Nielsen, R. “Counter-propagation networks”, IEEE First int. conference on neural networks, San Diego, vol.2, pp. 19–31 (1987)Google Scholar
  8. 46.
    Heskes, T.M., B. Kappen, “On-line learning processes in artificial neural networks”, in: Math. foundations of neural networks, Elsevier, Amsterdam, 199–233, (1993).Google Scholar
  9. 47.
    Kohonen, T., Self-Organizing Maps, second edition, Springer Verlag, 1997zbMATHCrossRefGoogle Scholar
  10. 48.
    Mandziuk, J., Shastri, L. Incremental class learning approach and its application to hand-written digit recognition, Proc. of the fifth int. conf. on neuro-information processing, Kitakyushu, Japan, Oct. 21–23, 1998Google Scholar
  11. 49.
    McClelland, J., B.L. McNaughton, and R.C. Reilly “Why there are Complementary Learning Systems in the Hippocampus and Neo-cortex: Insights from the Successes and Failures of Connectionist Models of Learning and Memory”, CMU TR PDP.CNS.94.1, March, (1994).Google Scholar
  12. 50.
    Mitchell, M.T., “Machine Learning”, MacGraw-Hill (1997)zbMATHGoogle Scholar
  13. 51.
    Moody, J., Darken, C, Fast learning in networks of locally-tuned processing units, Neural Computation, 1(2), 281–294 (1989)CrossRefGoogle Scholar
  14. 52.
    Platt, J., “A resource allocating network for function interpolation, Neural Computation, 3, 213–225 (1991)MathSciNetCrossRefGoogle Scholar
  15. 53.
    Rosipal, R., M. Koska, I. Farkas, “Prediction of chaotic time-series with a resource allocating RBF network, Neural Processing Letters, 10:26 (1997)Google Scholar
  16. 54.
    Saad, D. (ed) On-line learning in neural networks, Cambridge University Press, 1999Google Scholar
  17. 55.
    Schaal, S. and C. Atkeson, Constructive incremental learning from only local information, Neural Computation, 10, 2047–2084 (1998)CrossRefGoogle Scholar
  18. 56.
    Towel, G., J. Shavlik, and M. Noordewier, “Refinement of approximate domain theories by knowledge-based neural networks”, Proc. of the 8th National Conf. on Artificial Intelligence AAAI’90, Morgan Kaufmann, 861–866 (1990).Google Scholar
  19. 57.
    Topchy, A., O. Lebedko, V. Miagkikh and N. Kasabov, “Adaptive training of radial basis function networks based on co-operative evolution and evolutionary programming”, in: Progress in connectionist-based information systems, N. Kasabov et al (eds), Springer, 253–258 (1998)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2000

Authors and Affiliations

  • Nikola Kasabov
    • 1
  1. 1.Department of Information ScienceUniversity of OtagoDunedinNew Zealand

Personalised recommendations