Dense shattering and teaching dimensions for differentiable families (extended abstract)

Subscribe (Full Service)


	Search: The ACM Digital Library The Guide

	Feedback

Dense shattering and teaching dimensions for differentiable families (extended abstract)

Full text

Pdf (1.51 MB)

Source

Annual Workshop on Computational Learning Theory archive
Proceedings of the tenth annual conference on Computational learning theory table of contents

Nashville, Tennessee, United States

Pages: 143 - 151

Year of Publication: 1997

ISBN:0-89791-891-6

Author

A. Kowalczyk

Telstra Research Laboratories, 770 Blackburn Road, Clayton, Vic. 3168, Australia

Sponsors

AT&T Labs :
SIGACT: ACM Special Interest Group on Algorithms and Computation Theory
SIGART: ACM Special Interest Group on Artificial Intelligence
Vanderbilt University : Vanderbilt University

Publisher

ACM New York, NY, USA

Bibliometrics

Downloads (6 Weeks): 19, Downloads (12 Months): 28, Citation Count: 0

Additional Information:

references index terms collaborative colleagues

Tools and Actions:	Review this Article Save this Article to a Binder Display Formats: BibTeX EndNote ACM Ref

DOI Bookmark:	Use this link to bookmark this Article: http://doi.acm.org/10.1145/267460.267490 What is a DOI?

REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

	1	F. Albertini, E.D. Sontag, and V. Maillot. Uniqueness of weights for neural networks. In R. Mammone, editor, Artificial Neural Networks with Applications in Speech and Vision, pages 115-125, London, 1993. Chapman and Hall.
	2	Martin Anthony , Norman Biggs, Computational learning theory: an introduction, Cambridge University Press, New York, NY, 1992
	3	Anselm Blumer , A. Ehrenfeucht , David Haussler , Manfred K. Warmuth, Learnability and the Vapnik-Chervonenkis dimension, Journal of the ACM (JACM), v.36 n.4, p.929-965, Oct. 1989 [doi>10.1145/76359.76371]
	4	T.M. Cover. Geometrical and statistical properties of linear inequalities with applications to pattern recognition. IEEE Trans. Elec. Camp., EC-14:326334, 1965.
	5	Thomas M. Cover , Joy A. Thomas, Elements of information theory, Wiley-Interscience, New York, NY, 1991
	6	C. Fefferman. Reconstructing a neural net from its outputs. Revista Matematica Iberoamericana, 3:507-555, 1994.
	7	Sally A. Goldman , Michael J. Kearns, On the complexity of teaching, Proceedings of the fourth annual workshop on Computational learning theory, p.303-314, August 05-07, 1991, Santa Cruz, California, United States
	8	M. Golubitsky and V. Guillemin. Stable Mapping and Their Singufariries. Springer-Verlag, New York, 1973.
	9	P Koiran and E.D. Sontag. Neural networks with quadratic VC-dimension. In Adv. in NIPS 8, Cambridge, Ma., 1996. The MIT Press.
	10	A. Kowalczyk. Estimates of storage capacity of multilayer perceptron with threshold logic hidden units. submited.
	11	A. Kowalczyk. Counting function theorem for multilayer networks. In J.D. Cowan, G. Tesauro, and J. Al- Spector, editors, Advances in Neural Information Processing Systems, volume 6, pages 375-382. Morgan Kaufman Publishers, Inc., 1994.
	12	A. Kowalczyk and H. Ferrd. MLP can provably generalise much better than VC-bounds indicate. In Advances in Neural Information Processing Systems, volume 9. The MIT Press, 1997.
	13	Angus Macintyre , Eduardo D. Sontag, Finiteness results for sigmoidal “neural” networks, Proceedings of the twenty-fifth annual ACM symposium on Theory of computing, p.325-334, May 16-18, 1993, San Diego, California, United States [doi>10.1145/167088.167192]
	14	A. Sakurai. n-h-l networks store no less n h + 1 examples but sometimes no more. In Proceedings of the 1992 International Conference on Neural Networks, pages 111-936-111-94 1. IEEE, June 1992.
	15	J. Shawe-Taylor, P. Bartlett, R. Williamson, and M. Anthony. Structural risk minimisation over datadependent hierarchies. NeuroCOLT technical Report NC-TR-5 1, 1996.
	16	E. Sontag. Critical points for least-square problems involving certain analytic functions, with applications to sigmoidal nets. Advances in Computational Mathematics. Special Issue on Neural Networks, to appear.
	17	Eduardo D. Sontag, Remarks on interpolation and recognition using neural nets, Proceedings of the 1990 conference on Advances in neural information processing systems 3, p.939-945, October 1990, Denver, Colorado, United States
	18	E. Sontag. Shattering all sets of k points in "general position" requires (k - 1)/2 parameters. Report 96- 01, Rutgers Center for Systems and Control (SYCON)., February, 1996.
	19	Héctor J. Sussmann, Uniqueness of the weights for minimal feedforward nets with a given input-output map, Neural Networks, v.5 n.4, p.589-593, July-Aug. 1992 [doi>10.1016/S0893-6080(05)80037-1]
	20	Vladimir Vapnik, Estimation of Dependences Based on Empirical Data: Springer Series in Statistics (Springer Series in Statistics), Springer-Verlag New York, Inc., Secaucus, NJ, 1982
	21	Vladimir N. Vapnik, The nature of statistical learning theory, Springer-Verlag New York, Inc., New York, NY, 1995