Abstract
The capacity or Vapnik-Chervonenkis dimension of a feedforward neural architecture is the maximum number of input patterns that can be mapped correctly to fixed arbitrary outputs. So far it is known that the upper bound for the capacity of two-layer feedforward architectures with independent weights depends on the number of connections in the neural architecture [1].
In this paper we focus on the capacity of multilayer feedforward networks structured by shared weights. We show that these structured architectures can be transformed into equivalent conventional multilayer feed-forward architectures. Known estimations for the capacity are extended to achieve upper bounds for the capacity of these general multi-layer feedforward architectures. As a result an upper bound for the capacity of structured architectures is derived that increases with the number of independent network parameters. This means that weight sharing in a fixed neural architecture leads to a significant reduction of the upper bound of the capacity.
This is a preview of subscription content, log in via an institution.
Preview
Unable to display preview. Download preview PDF.
References
E. B. Baum, D. Haussler: What Size Net gives Valid Generalization?, Advances in Neural Information Processing Systems, D. Touretzky, Ed., Morgan Kaufmann, (1989).
T. M. Cover: Geometrical and Statistical Properties of Systems of Linear Inequalities with Applications in Pattern Recognition, IEEE Transactions on Electronic Computers, Vol. 14, 326–334, (1965).
P. Koiran, E.D. Sontag: Neural Networks with Quadratic VC Dimension, Neuro-COLT Technical Report Series, NC-TR-95-044, London, (1995)
S. Kröner, R. Moratz, H. Burkhardt: An adaptive invariant transform using neural network techniques, in Proceedings of EUSIPCO 94, 7th European Signal Processing Conf., Holt et al. (Ed.), Vol. III, 1489–1491, Edinburgh, (1994).
Y. le Cun: Generalization and Network Design Strategies, Connectionism in Perspective, R. Pfeiffer, Z. Schreter, F. Fogelman-Soulié, L. Steels (Eds.), Elsevier Science Publishers B.V. 143–155, North-Holland, (1989).
W. Maass: Vapnik-Chervonenkis Dimension of Neural Nets, Preprint, Technische Universität Graz, (1994).
G. J. Mitchison, R. M. Durbin: Bounds on the Learning Capacity of Some Multi-Layer Networks, Biological Cybernetics, Vol.60, No. 5, 345–356, (1989).
P. Rieper: Zur Speicherfähigkeit vorwärtsgerichteter Architekturen künstlicher neuronaler Netze mit gekoppelten Knoten, Diplomarbeit, Universität Hamburg, (1994).
V. Vapnik: Estimation of Dependences Based on Empirical Data, Springer-Verlag, Berlin, (1982).
A. Waibel: Modular Construction of Time-Delay Neural Networks for Speech Recognition, Neural Computation, Vol.1, 39–46, (1989).
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1996 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Kröner, S., Moratz, R. (1996). Capacity of structured multilayer networks with shared weights. In: von der Malsburg, C., von Seelen, W., Vorbrüggen, J.C., Sendhoff, B. (eds) Artificial Neural Networks — ICANN 96. ICANN 1996. Lecture Notes in Computer Science, vol 1112. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-61510-5_93
Download citation
DOI: https://doi.org/10.1007/3-540-61510-5_93
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-61510-1
Online ISBN: 978-3-540-68684-2
eBook Packages: Springer Book Archive