Abstract
In this paper, a new constructive approach for the automatic definition of feedforward neural networks (FNNs) is introduced. Such approach (named MASCoNN) is multiagent-oriented and, thus, can be regarded as a kind of hybrid (synergetic) system. MASCoNN centers upon the employment of a two-level hierarchy of agent-based elements for the progressive allocation of neuronal building blocks. By this means, an FNN can be considered as an architectural organization of reactive neural agents, orchestrated by deliberative coordination entities via synaptic interactions. MASCoNN was successfully applied to implement nonlinear dynamic systems identification devices and some comparative results, involving alternative proposals, are analyzed here.
Keywords
- Neural Network
- Multiagent System
- Nonlinear Dynamic System
- Feedforward Neural Network
- Synaptic Interaction
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Dahmen, W., Micchelli, C.A.: Some remarks on ridge functions. Approximation Theory and its Applications 3(2-3), 139–143 (1987)
Davis, P.J.: Interpolation & Approximation. Dover Publications, New York (1975)
Fahlman, S.E., Lebiere, C.: The cascade-correlation learning architecture. In: Touretzky, D.S. (ed.) Advances in Neural Information Processing Systems, vol. 2, pp. 524–532. Morgan Kaufmann, San Francisco (1990)
Ghosh, J.: Neural-symbolic hybrid systems. In: Padget, M., et al. (eds.) The Handbook of Applied Computational Intelligence. CRC Press, Boca Raton (2001)
Goonatilake, S., Khebbal, S. (eds.): Intelligent Hybrid Systems. Wiley, Chichester (1995)
Härdle, W.: Applied Nonparametric Regression. Cambridge University Press, Cambridge (1990)
Haykin, S.: Neural Networks–A Comprehensive Foundation. Prentice Hall, Englewood Cliffs (1999)
Hwang, J., Lay, S., Maechler, M., Martin, D., Schimert, J.: Regression modeling in backpropagation and project pursuit learning. IEEE Trans. on Neural Networks 5(3), 342–353 (1994)
Kwok, T.-Y., Yeung, D.-Y.: Constructive algorithms for structure learning in feedforward neural networks for regression problems. IEEE Trans. on Neural Networks 8(3), 630–645 (1997)
Medskar, L.A.: Hybrid Intelligent Systems. Kluwer Academic Publishers, Dordrecht (1995)
Narendra, K., Parthasarathy, K.: Identification and control of dynamical systems using neural networks. IEEE Trans. on Neural Networks 1(1), 4–27 (1990)
Nrgaard, M., Ravn, O., Poulsen, N.K., Norgaard, P.M., Hansen, L.K.: Neural Networks for Modelling and Control of Dynamic Systems: A Practitioner’s Handbook. In: Advanced Textbooks in Control and Signal Processing. Springer, Heidelberg (2000)
Pham, K.M.: The neurOagent: A neural multi-agent approach for modelling, distributed processing and learning. In: Goonatilake and Khebbal [5], ch. 12, pp. 221–244
Reed, R.: Pruning algorithms–A survey. IEEE Trans. on Neural Networks 4(5), 740–747 (1993)
Scherer, A., Schlageter, G.: A multi-agent approach for the integration of neural networks and expert systems. In: Goonatilake and Khebbal [5], ch. 9, pp. 153–173
Selfridge, O.G.: Pandemonium: A paradigm for learning. In: Proc. Symp. Held Physical Lab.: Mechanisation Thought Processing, pp. 511–517, London (1958)
Śmieja, F.J.: The pandemonium system of reflective agents. IEEE Trans. on Neural Networks 7(1), 97–106 (1996)
Taha, I., Ghosh, J.: Symbolic interpretation of artificial neural networks. IEEE Trans. on Knowledge and Data Eng. 11(3), 448–463 (1999)
Zuben, F.J.V., Netto, M.: Projection pursuit and the solvability condition applied to constructive learning. In: Proc. of the International Joint Conference on Neural Networks, vol. 2, pp. 1062–1067 (1997)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2003 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lima, C.A.M., Coelho, A.L.V., Von Zuben, F.J. (2003). A Multiagent-Based Constructive Approach for Feedforward Neural Networks. In: R. Berthold, M., Lenz, HJ., Bradley, E., Kruse, R., Borgelt, C. (eds) Advances in Intelligent Data Analysis V. IDA 2003. Lecture Notes in Computer Science, vol 2810. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-45231-7_43
Download citation
DOI: https://doi.org/10.1007/978-3-540-45231-7_43
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-40813-0
Online ISBN: 978-3-540-45231-7
eBook Packages: Springer Book Archive