Abstract
This paper describes the Combinatorial Neural Model, a high order neural network suitable for classification tasks. The model is based on the fuzzy sets theory, neural sciences and expert knowledge analysis results. The model presents interesting properties such as: modularity, explanation capacity, concomitant knowledge and data representation, high speed of training, incremental learning, generalization capacity, feature selection, processing of uncertain and incomplete data, fault tolerance.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
Giles C.L. and Maxwell T. (1987) Learning, invariance, and generalization in high-order neural networks, Applied Optics, 26 (1987), 4972–4978
Greco G. and Rocha A.F. (1987) The fuzzy logic of to it understanding, Fuzzy Sets and Systems 23 (1987), 347–360
Leão B.L. and Rocha A.F. (1990) Proposed methodology for knowledge acquisition: a study on congenital heart diseases diagnosis, Methods of Inf. in Medicine, 29 (1990), 30–40
Machado R.J., Rocha A.F. and Leão B.F. (1991) Calculating the mean knowledge representation from multiple experts. To appear in Multiperson Decision Making Models Using Fuzzy Sets and Possibility Theory, (Fedrizzi M., Kacprzyk J., eds), Kluwer Academic Publishers
Machado R.J. and Rocha A.F. (1989) Handling knowledge in high order neural networks: the combinatorial neural model, IBM Rio Scientific Center Technical Report CCR076
Machado R.J., Rocha A.F. et al (1990) Heuristic learning expert system, Proceedings of 7o Simpósio Brasileiro de Inteligência Artificial, Campina Grande, (1990), 1–7
Miller G.A. (1956) The magical number seven, plus or minus two: some limits on our capacity for processing information, Psychological Review 63 (1956), 81–97
Rocha A.F. et al (1989) Handling uncertainty in medical reasoning, III International Fuzzy Sets Association Conference, USA
Rocha A.F., Laginha M.P.R., Machado R.J., Sigulem D., Anção M. (1990) Declarative and procedural knowledge — two complementary tools for expertise. In Approximate Reasoning Tools for Artificial Intelligence (Verdegay J.L., Delgado M., eds), Verlag Tuv
Zadeh L.A. (1965) Fuzzy sets, Information and Control 8 (1965), 338–353
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1991 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Machado, R.J., Da Rocha, A.F. (1991). The combinatorial neural network: A connectionist model for knowledge based systems. In: Bouchon-Meunier, B., Yager, R.R., Zadeh, L.A. (eds) Uncertainty in Knowledge Bases. IPMU 1990. Lecture Notes in Computer Science, vol 521. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0028145
Download citation
DOI: https://doi.org/10.1007/BFb0028145
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-54346-6
Online ISBN: 978-3-540-47580-4
eBook Packages: Springer Book Archive