Abstract
It has remained an open question whether there exist product unit networks with constant depth that have superlinear VC dimension. In this paper we give an answer by constructing two-hidden-layer networks with this property. We further show that the pseudo dimension of a single product unit is linear. These results bear witness to the cooperative effects on the computational capabilities of product unit networks as they are used in practice.
Work supported by the ESPRIT Working Group in Neural and Computational Learning II, NeuroCOLT2, No. 27150. A longer (9-page) version of this paper is available from http://www.ruhr-uni-bochum.de/lmi/mschmitt/. Complete proofs also appear in [9]
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
M. Anthony and P. L. Bartlett. Neural Network Learning: Theoretical Foundations. Cambridge University Press, Cambridge, 1999.
R. Durbin and D. Rumelhart. Product units: A computationally powerful and biologically plausible extension to backpropagation networks. Neural Computation, 1:133–142, 1989.
A. Ismail and A. P. Engelbrecht. Global optimization algorithms for training product unit neural networks. In International Joint Conference on Neural Networks IJCNN’2000, vol. I, pp. 132–137, IEEE Computer Society, Los Alamitos, CA, 2000.
P. Koiran and E. D. Sontag. Neural networks with quadratic VC dimension. Journal of Computer and System Sciences, 54:190–198, 1997.
L. R. Leerink, C. L. Giles, B. G. Horne, and M. A. Jabri. Learning with product units. In G. Tesauro, D. Touretzky, and T. Leen, editors, Advances in Neural Information Processing Systems 7, pp. 537–544, MIT Press, Cambridge, MA, 1995.
W. Maass. Neural nets with super-linear VC-dimension. Neural Computation, 6:877–884, 1994.
W. Maass and G. Turán. Lower bound methods and separation results for on-line learning models. Machine Learning, 9:107–145, 1992.
A. Sakurai. Tighter bounds of the VC-dimension of three layer networks. In Proceedings of the World Congress on Neural Networks, vol. 3, pp. 540–543. Erlbaum, Hillsdale, NJ, 1993.
M. Schmitt. On the complexity of computing and learning with multiplicative neural networks. Neural Computation, to appear.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2001 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Schmitt, M. (2001). Product Unit Neural Networks with Constant Depth and Superlinear VC Dimension. In: Dorffner, G., Bischof, H., Hornik, K. (eds) Artificial Neural Networks — ICANN 2001. ICANN 2001. Lecture Notes in Computer Science, vol 2130. Springer, Berlin, Heidelberg. https://doi.org/10.1007/3-540-44668-0_36
Download citation
DOI: https://doi.org/10.1007/3-540-44668-0_36
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-42486-4
Online ISBN: 978-3-540-44668-2
eBook Packages: Springer Book Archive