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).
Preview
Unable to display preview. Download preview PDF.
References
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.
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.
Melanie Hilario. Bias and knowledge in symbolic and connectionist induction. Technical report, Centre Universitaire d'Informatique, Université de Genève, Genève, Switzerland, 1997.
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.
Donald Michie, David J. Spiegelhalter, and Charles C. Taylor, editors. Machine Learning, Neural and Statistical Classification. Ellis Horwood, 1994.
A. Prieditis and S. Russell, editors. Proceedings of the 11th International Conference on Machine Learning, Tahoe City, CA, 1995. Morgan Kaufmann.
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.
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.
Author information
Authors and Affiliations
Editor information
Rights 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