Abstract
Multi-nets promise an improved performance over monolithic neural networks by virtue of their distributed implementation. Modular neural networks are multi-nets based on an judicious assembly of functionally different parts. This can be viewed as again a monolithic network, but with more complex neurons (the neural modules). Therefore they will share the same learning problems, notably the unlearning effect. In this paper we will look more closely into the reasons for unlearning and discuss how this can be applied to detect novelties.
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
Sharkey, A.J.C. (ed.): Combining artificial neural nets, Heidelberg: Springer 1999.
Caelli, T. Guan, L. Wan, W.: Modularity in Neural Computing, Proc. of the IEEE 87, pp. 1497–1518 (1999).
Macready, W.G. Siapas, A.G. Kauffman, S.A.: Criticality and parallelism in combinatorial optimization, Science 271, pp. 56–59 (1996).
Barakova, E.I.: Learning Reliability: a study on indecisiveness in sample selection, Ph.D. thesis (Groningen University, Groningen) 1999.
Schuermann, B.: Applications and Perspectives of Artificial Neural Networks, VDI Berichte 1526, pp. 1–14 (2000).
Sprinkhuizen-Kuyper, I.G. Boers, E.J.W.: A local minimum for the 2-3-1 XOR network, IEEE Tr. on Neural Networks 10, pp. 968–971, (1999).
Venema, R.S. Spaanenburg, L.: Learning feedforward networks, this proceeding.
Saad, D.: Explicit symmetries and the capacity of multilayer neural networks, Journal Physics A 27, pp. 2719–2734 (1994).
Spaanenburg, L. Jansen, W.J. Nijhuis, J.A.G.: Over multiple rule-blocks to modular nets, Proceedings EUROMICRO’97, pp. 698–705 (1997).
Yamauchi, K. Yamaguchi, Y. Ishii, N.: Incremental learning methods with retrieving of interfered patterns, IEEE Tr. on Neural Networks 10, pp. 1351–1365 (1999).
TerBrugge, M.H. Nijhuis, J.A.G. Spaanenburg, L.: License-Plate Recognition, pp. 263–296, in: Jain, L.C. Lazzarini, B.: Intelligent Techniques in Character Recognition: Practical Applications, CRC Press 199
Yu, X.L. Chen, G.K.C. Cheng, S.: Dynamic learning rate optimization of the back-propagation Algorithm, IEEE Tr. on Neural Networks 6, pp. 669–677 (1995).
VanVeelen, M. Nijhuis, J.A.G. Spaanenburg, L.: Process fault detection through quantitative analysis of learning in neural networks, Proceedings ProRISC’2000, pp. 557–565 (2000).
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Wien
About this paper
Cite this paper
Spaanenburg, L. (2001). Unlearning in Feed-Forward Multi-Nets. In: Kůrková, V., Neruda, R., Kárný, M., Steele, N.C. (eds) Artificial Neural Nets and Genetic Algorithms. Springer, Vienna. https://doi.org/10.1007/978-3-7091-6230-9_25
Download citation
DOI: https://doi.org/10.1007/978-3-7091-6230-9_25
Publisher Name: Springer, Vienna
Print ISBN: 978-3-211-83651-4
Online ISBN: 978-3-7091-6230-9
eBook Packages: Springer Book Archive