Skip to main content

An agent-based operational model for hybrid connectionist-symbolic learning

  • Artificial Neural Nets Simulation and Implementation
  • Conference paper
  • First Online:
Engineering Applications of Bio-Inspired Artificial Neural Networks (IWANN 1999)

Part of the book series: Lecture Notes in Computer Science ((LNCS,volume 1607))

Included in the following conference series:

Abstract

Hybridization of connectionist and symbolic systems is being proposed for machine learning purposes in many applications for different fields. However, a unified framework to analyse and compare learning methods has not appeared yet. In this paper, a multiagent-based approach is presented as an adequate model for hybrid learning. This approach is built upon the concept of bias.

This research is funded in part by the Commission of the European Communities under the ESPRIT Basic Research Project MIX: Modular Integration of Connectionist and Symboic Processing in Knowledge Based Systems, ESPRIT-9119, and by CYCIT, the Spanish Council for Research and Development, under the project M2D2: Metaaprendizaje en Minería de Datos Distribuida, TIC97-1343. The MIX consortium is formed by the following institutions and companies: Institute National de Recherche en Informatique et en Automatique (INRIA-Lorraine/CRIN-CNRS, France), Centre Universitaire d'Informatique (Université de Genève, Switzerland), Institute d'Informatique et de Mathématiques Appliquées de Grenoble (France), Kratzer Automatisierung (Germany), Fakultät für Informatik (Technische Universität München, Germany) and Dep. Ingeniería de Sistemas Telemáticos (Universidad Politécnica de Madrid, Spain).

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Institutional subscriptions

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. P. Chan and S. Stolfo. A comparative evaluation of voting and meta-learning on partitioned data. In Prieditis and Russell [6], Proceedings of the 11th International Conference on Machine Learning, Tahoe City, CA, 1995. Morgan Kaufmann, pages 90–98.

    Google Scholar 

  2. J. Gama and P. Brazdil. Characterization of classification algorithms. In E. Pinto-Ferreira and N. Mamede, editors, Progress in Artificial Intelligence. Proceedings of the 7th Portuguese Conference on Artificial Intelligence (EPIA-95), pages 189–200. Springer-Verlag, 1995.

    Google Scholar 

  3. Melanie Hilario. Bias and knowledge in symbolic and connectionist induction. Technical report, Centre Universitaire d'Informatique, Université de Genève, Genève, Switzerland, 1997.

    Google Scholar 

  4. R. Kohavi and G. John. Automatic parameter selection by minimizing estimated error. In Prieditis and Russell [6] Proceedings of the 11th International Conference on Machine Learning, Tahoe City, CA, 1995, Morgan Kaufmann, pages 304–312.

    Google Scholar 

  5. Donald Michie, David J. Spiegelhalter, and Charles C. Taylor, editors. Machine Learning, Neural and Statistical Classification. Ellis Horwood, 1994.

    Google Scholar 

  6. A. Prieditis and S. Russell, editors. Proceedings of the 11th International Conference on Machine Learning, Tahoe City, CA, 1995. Morgan Kaufmann.

    Google Scholar 

  7. L. Rendell, R. Seshu, and D. Tcheng. Layered-concept learning and dinamically variable bias management. In Proceedings of the 10th International Joint Conference on Artificial Intelligence, pages 308–314, Milan, Italy, 1987. Morgan Kaufmann.

    Google Scholar 

  8. G. Widmer. Recognition and exploitation of contextual cues via incremental metalearning. Technical Report OFAI-TR-96-01, Austria Research Institute for Artificial Intelligence, Vienna, Austria, 1996.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Editor information

José Mira Juan V. Sánchez-Andrés

Rights and permissions

Reprints and permissions

Copyright information

© 1999 Springer-Verlag Berlin Heidelberg

About this paper

Cite this paper

González, J.C., Velasco, J.R., Iglesias, C.A. (1999). An agent-based operational model for hybrid connectionist-symbolic learning. In: Mira, J., Sánchez-Andrés, J.V. (eds) Engineering Applications of Bio-Inspired Artificial Neural Networks. IWANN 1999. Lecture Notes in Computer Science, vol 1607. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0100471

Download citation

  • DOI: https://doi.org/10.1007/BFb0100471

  • Published:

  • Publisher Name: Springer, Berlin, Heidelberg

  • Print ISBN: 978-3-540-66068-2

  • Online ISBN: 978-3-540-48772-2

  • eBook Packages: Springer Book Archive

Publish with us

Policies and ethics