Abstract
Just as a busy kitchen can be more efficient than an idle one, Kleinrock showed 35 years ago that heavily used networks admit simple heuristic approximations with excellent quantitative accuracy. We describe a number of different examples in which having many parameters actually facilitates computation and we suggest connections with geometric phenomena in high-dimensional spaces. It seems that in several interesting and quite general situations, dimensionality may be a blessing in disguise provided that some suitable form of computing is used which can deal with it.
Article Footnote
The author thanks the signal processing group of ENSEEIHT in Toulouse and the Institute of Computer Science in Prague for helpful research support.
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
A. Barron, “Universal approximation bounds for a superposition of a sigmoidal function,” IEEE Transactions on Information Theory, vol. 39, no. 3, pp. 930–945, 1993.
J. L. Bentley, D. S. Johnson, F. T. Leighton and C. C. McGeoch, “An experimental study of bin packing,” Proc. 21st Ann. Conf. on Communication,Control and Computing U. of Illinois, Urbana, pp. 51–60, 1983.
J. L. Bentley and L. A. McGeoch, “Some unexpected expected behavior results for bin packing,” Proc. 16th Ann. Symp. on Theory of Computing,pp. 279–288, 1984.
J. H. Conway and N. J. A. Sloane, Sphere packings, lattices and groups, Springer-Verlag, New York, 1988.
R. Courant, Integral and Differential Calculus,Vol 2, Interscience, New York, 1936.
M. Desmurget, C. Prablanc, Y. Rossetti, M. Arzi, Y. Paulignan, C. Urquizar et J-C. Mignot, “Postural and synergic control for three-dimensional movements of reaching and grasping,” J. of Neurobiology vol. 74, pp. 905–910, 1995.
S. Floyd and R. M. Karp, “FFD bin packing for item sizes with uniform distributions on [0, 1/2],” Algorithmica,vol. 6, pp. 222–240, 1991.
M. R. Garey and D. S. Johnson, Computers and Intractability, W. H. Freeman, San Francisco, 1979.
B. Ghosh, “Random distances within a rectangle and between two rectangles,” Bull. Calcutta Math. Soc., vol. 43, pp. 17–24, 1951.
Golovina and I. M. Yaglom, Induction in Geometry, Mir Press, Moscow, 1979.
R. W. Hamming, Coding and Information Theory, Prentice-Hall, Englewood Cliffs, NJ, 1986.
S. H. Hechler and P. C. Kainen, “On the immersion of digraphs in cubes,” Israel J. of Mathematics, vol. 18, pp. 221–233, 1974.
D. S. Johnson, A. Demers, J. D. Ullman, M. R. Garey and R. L. Graham, “Worst-case performance bounds for simple one-dimensional packing algorithms,” SIAM J. Computing, vol. 3, pp. 299–325, 1974.
P. C. Kainen, “On parallel heuristics,” Neural Network World, vol. 5, pp. 281–286, 1991.
P. C. Kainen, “Graph heuristics for biomolecules,” Nanobiology vol. 1, pp. 469–476, 1992.
P. C. Kainen, “Abstract computation in biology,” Proc. of the Amiens Conference ECHO,1996.
P. C. Kainen, “A uniform bound for rearranged vector sums,” Geombinatorics,vol. 3, pp. 10–12, 1993.
P. C. Kainen and V. Kúrková, “On quasiorthogonal dimension of euclidean space,” Applied Math. Lett.,vol. 6, pp. 7–10, 1993.
L. Kleinrock, Communication Nets, Dover, New York, 1972.
V. Kúrková and P. C. Kainen, “A geometric method to obtain error-correcting classification by neural networks with fewer hidden units,” ICNN96, pp. 1227–1232, IEEE, Piscataway, NJ, 1996.
V. Kúrková, P. C. Kainen and V. Kreinovich. “Estimates of the number of hidden units and variation with respect to half-spaces,” Neural Networks, to appear.
D. M. Lazoff and A. T. Sherman, “Expected wire length between two randomly chosen terminals,” Problem 95–6, SIAM Review, vol. 38, pp. 321–324, 1996.
T. J. Sejnowski and C. Rosenberg, “Parallel networks that learn to pronounce English text,” Complex Systems, vol. 1, pp. 145–187, 1987.
J. Spencer, Ten Lectures on the Probabilistic Method, CBMS-NSF Regional Conf. Series in Appl. Math. 52, SIAM, Philadelphia, 1987.
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1997 Springer Science+Business Media New York
About this chapter
Cite this chapter
Kainen, P.C. (1997). Utilizing Geometric Anomalies of High Dimension: When Complexity Makes Computation Easier. In: Kárný, M., Warwick, K. (eds) Computer Intensive Methods in Control and Signal Processing. Birkhäuser, Boston, MA. https://doi.org/10.1007/978-1-4612-1996-5_18
Download citation
DOI: https://doi.org/10.1007/978-1-4612-1996-5_18
Publisher Name: Birkhäuser, Boston, MA
Print ISBN: 978-1-4612-7373-8
Online ISBN: 978-1-4612-1996-5
eBook Packages: Springer Book Archive