Abstract
The iterated difference of polyhedra V = P 1(P 2(...P k )...) has been proposed independently in [11] and [7] as a sufficient condition for V to be exactly computable by a two-layered neural network. An algorithm checking whether V ⊂ ℝ d is an iterated difference of polyhedra is proposed in [11]. However, this algorithm is not practically usable because it has a high computational complexity and it was only conjectured to stop with a negative answer when applied to a region which is not an iterated difference of polyhedra. This paper sheds some light on the nature of iterated difference of polyhedra. The outcomes are : (i) an algorithm which always stops after a small number of iterations, (ii) sufficient conditions for this algorithm to be polynomial and (iii) the proof that an iterated difference of polyhedra can be exactly computed by a two-layered neural network using only essential hyperplanes.
Preview
Unable to display preview. Download preview PDF.
References
G. Brightwell, C. Kenyon, and H. Paugam-Moisy. Multilayer neural networks: one or two hidden layers ? Technical Report NC-TR-97-001, NeuroCOLT Technical Report Series, 1997.
Gavin J. Gibson and Colin F. N. Cowan. On the decision regions of multilayer perceptrons. Proceedings of the IEEE, 78(10):1590–1594, 1990.
Gavin J. Gibson. Exact classification with 2-layered nets. J. Computer and System Sciences, 1996.
R. P. Lippmann. An introduction to computing with neural nets. IEEE, Acoustic, Speech and Signal Processing, 4:4–22, 1987.
Eddy Mayoraz. On variations of the convex hull operator. IDIAP-RR 96-06, IDIAP, 1996. ftp://ftp.idiap.ch/pub/mayoraz/Publications/RRR-06-96.ps.gz.
Eddy Mayoraz. On the complexity of recognizing regions of ℝd computable by a two-layered perceptron. IDIAP-RR 97-05, IDIAP, 1997. ftp://ftp.idiap.ch/pub/mayoraz/Publications/RRR-05-97.ps.gz.
Ron Shonkwiler. Separating the vertices of n-cubes by hyperplanes and its application to artificial neural networks. IEEE Transactions on Neural Networks, 4(2):343–347, March 1993.
Catherine Z. W. Hassell Sweatman, Gavin J. Gibson, and Bernard Mulgrew. Exact classification with two-layer neural nets in n dimensions. submitted, 1996.
Patrick J. Zwietering. The Complexity of Multi-Layered Perceptrons. PhD thesis, University of Eindhoven, 1994.
P. J. Zwietering, E. H. L. Aarts, and J. Wessels. The design and complexity of exact multilayered perceptrons. International Journal of Neural Systems, 2:185–199, 1991.
P. J. Zwietering, E. H. L. Aarts, and J. Wessels. Exact classification with twolayered perceptrons. International Journal of Neural Systems, 3(2):143–156, 1992.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1997 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Mayoraz, E. (1997). On the complexity of recognizing iterated differences of polyhedra. In: Gerstner, W., Germond, A., Hasler, M., Nicoud, JD. (eds) Artificial Neural Networks — ICANN'97. ICANN 1997. Lecture Notes in Computer Science, vol 1327. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0020200
Download citation
DOI: https://doi.org/10.1007/BFb0020200
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-63631-1
Online ISBN: 978-3-540-69620-9
eBook Packages: Springer Book Archive