Abstract
This work belongs to the field of hybrid systems for Artificial Intelligence (AI). It concerns the study of ”gradual” rules, which makes it possible to represent correlations and modulation relations between variables. We propose a set of characteristics to identify these gradual rules, and a classification of these rules into ”direct” rules and ”modulation” rules. In neurobiology, pre-synaptic neuronal connections lead to gradual processing and modulation of cognitive information. While taking as a starting point such neurobiological data, we propose in the field of connectionism the use of ”Sigma-Pi” connections to allow gradual processing in AI systems. In order to represent as well as possible the modulation processes between the inputs of a network, we have created a new type of connection, ”Asymmetric Sigma-Pi” (ASP) units. These models have been implemented within a pre-existing hybrid neuro-symbolic system, the INSS system, based on connectionist nets of the ”Cascade Correlation” type. The new hybrid system thus obtained, INSS-Gradual, allows the learning of bases of examples containing gradual modulation relations. ASP units facilitate the extraction of gradual rules from a neural network.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Alexandre, F.: Intelligence Neuromimétique. Mémoire pour l’obtention de l’habilitation à diriger des recherches. Henri Poincaré University - Nancy I. France (June 1997)
Bouchon-Meunier, B.: La Logique Floue et ses Applications, October 1995. Addison-Wesley, France (1995)
Davis, H.: Using Models of Dynamic Behaviour in Expert Systems. Neuvième Journées Internationales sur Les Systèmes Experts et leurs Applications, Avignon, France, May 29-June 2 (1989)
Després, S.: Topoi et Gestion des Connaissances, ch. 5, Edit. Raccah, P.-Y. Masson, Paris (1996)
Dubois, D., Prade, H.: Prédicats Graduels et Modalités Nuancées. Le Courrier du CNRS. Sciences Cognitives. CNRS (79) (October 1992)
Fahlman, S.E., Lebiere, C.: The Cascade-Correlation Learning Architecture. Carnegie Mellon University. Technical Report. CMU-CS-90-100 (1990)
Giacometi, A.: Modèles Hybrides de l’Expertise. PhD Thesis, LIFIA-IMAG, Grenoble - France (November 1992)
Gurney, K.: Alternative Node Types. Dept. Human Sciences, Brunel University Uxbridge, Middx (1997), Notes in http://pikas.inf.tu-dresden.de/~ihle/NNcourse/NOTES/18/18.html
Osório, F.S.: INSS - Un Système Hybride Neuro-Symbolique pour l’Apprentissage Automatique Constructif. PhD Thesis, LEIBNIZ-IMAG, Grenoble – France (February 1998)
Quinlan, R.: Combining Instance-Based and Model-Based Reasoning. In: Proceedings on the Tenth International Conference of Machine Learning, University of Massachusetts, Amherst, Morgan Kaufmann, San Francisco (1993)
Raccah, P.-Y.: Chapter 10 of Sémantique et Cognition: Catégories, Prototypes et Typicalité. Dubois, D (Ed). Edit. CNRS (1991)
Reyes-Salgado, G.: Connaissances de haut niveau dans les systèmes hybrides neurosymboliques. PhD Thesis, LEIBNIZ-IMAG, Grenoble – France (June 2001)
Rumelhart, D.E., McClelland, J.L.: PDP Research Group. In: Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Foundations, vol. 1, The MIT Press, Cambridge (1986)
Smyth, D., Phillips, W.A., Kay, J.: Measures for Investigating the Contextual Modulation of Information Transmission. In: Network: Computation in Neural Systems, UK, vol. 7, pp. 307–316 (1996)
Thimm, G.: Optimisation of High Order Perceptrons. PhD Thesis. École Polytechnique Fédérale de Lausanne, Switzerland (1997)
Thrun, S.B., et al.: The Monk’s Problem – A Performance Comparison of Different Learning Algorithms. Carnegie Mellon University - CMU, Technical Report CMU-CS-91-197 (December 1991), Web http://www.cs.cmu.edu/~thrun/ , Ftp ftp://archive.cis.ohio-state.edu/pub/neuroprose
Tickle, A.B., Andrews, R., Golea, M., Diederich, J.: The Truth Will Come to Light: Directions and Challenges in Extracting the Knowledge Embedded Within Trained Artificial Neural Networks. IEEE Transactions on Neural Networks, 9(6) (November 1998)
Towell, G.: Symbolic Knowledge and Neural Networks: Insertion, Refinement and Extraction. Ph.D. Thesis. Univ. of Wisconsin - Madison, USA (1991)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Salgado, G.R., Amy, B. (2004). Treatment of Gradual Knowledge Using Sigma-Pi Neural Networks. In: Monroy, R., Arroyo-Figueroa, G., Sucar, L.E., Sossa, H. (eds) MICAI 2004: Advances in Artificial Intelligence. MICAI 2004. Lecture Notes in Computer Science(), vol 2972. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24694-7_88
Download citation
DOI: https://doi.org/10.1007/978-3-540-24694-7_88
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21459-5
Online ISBN: 978-3-540-24694-7
eBook Packages: Springer Book Archive