On the optimal capacity of binary neural networks

Subscribe (Full Service)


	Search: The ACM Digital Library The Guide

	Feedback

On the optimal capacity of binary neural networks: rigorous combinatorial approaches

Full text

Pdf (805 KB)

Source

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

Santa Cruz, California, United States

Pages: 240 - 249

Year of Publication: 1995

ISBN:0-89791-723-5

Authors

Jeong Han Kim	Mathematical Sciences Research Center, AT&T Bell Laboratories, Murray Hill, NJ
James R. Roche	Mathematical Sciences Research Center, AT&T Bell Laboratories, Murray Hill, NJ

Sponsors

SIGACT: ACM Special Interest Group on Algorithms and Computation Theory
SIGART: ACM Special Interest Group on Artificial Intelligence
University of California : University of California

Publisher

ACM New York, NY, USA

Bibliometrics

Downloads (6 Weeks): 17, Downloads (12 Months): 38, 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/10.1145/225298.225327 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	N. Alon and J. Spencer. The ProbabzIistic Method. Wiley, 1992.
	2	E. Barkai and I. Kanter. Storage capacity of a multilayer neural network with binary weights. Europhys. Left., 14:107-112, 1991.
	3	L. Breiman. Probabzlity. Addison-Wesley, 1968.
	4	T. M. Cover. Geometrical and statistical properties of systems of linear inequalities with applications in pattern recognition. IEEE Transactions or~ Electronzc Computers, 14:326-331, 1965.
	5	Z. Ffiredi. Random polytopes in the d-dimensional cube. Dzscrete Comput. Geom., 1:315 319, 1986.
	6	E. Gardner. Maximum storage capacity in neural networks. Europhys Lett., 4:481-485, 1987.
	7	E. Gardner. The space of interactions in neural network models. J. Phys. A, 21:257-270, 1988.
	8	E. Gardner and B. Derrida. Optimal storage properties of neural network models. J. Phys. A, 21:271-284, 1988.
	9	Mostefa Golea , Mario Marchand, Average case analysis of the clipped Hebb rule for nonoverlapping perception networks, Proceedings of the sixth annual conference on Computational learning theory, p.151-157, July 26-28, 1993, Santa Cruz, California, United States [doi>10.1145/168304.168323]
	10	G. Gyorgyi. First-order transition to perfect generalization in a neural network with binary synapses. Phys. Rev. A, 41:7097-7100, 1990.
	11	David Haussler , H. Sebastian Seung , Michael Kearns , Naftali Tishby, Rigorous learning curve bounds from statistical mechanics, Proceedings of the seventh annual conference on Computational learning theory, p.76-87, July 12-15, 1994, New Brunswick, New Jersey, United States [doi>10.1145/180139.181018]
	12	D. O. Hebb. The Organization of Behavwr. Wiley, New York, 1949.
	13	Geoffrey E. Hinton , J. A. Anderson, Parallel Models of Associative Memory, Lawrence Erlbaum Associates, Inc., Mahwah, NJ, 1989
	14	J. J. Hopfield. Nem'al networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences of the United States of America, 79:2554- 2558, 1982.
	15	J. Kahn, J. Koml6s, and E. Szemerddi. Singularity probability for random ~1 matrices. Preprint, 1993.
	16	H. K6hler, S. Diederich, W. Kinzel, and M. Opper. Learning algorithm for a neural network with binary synapses. Z. Phys. B, 78:333-342, 1990.
	17	J. H. Kim. {n preparation.
	18	T. Kohonen, Self-organization and associative memory: 3rd edition, Springer-Verlag New York, Inc., New York, NY, 1989
	19	T. Kohonen. State of the art in neural computing. IEEE First International Conference on Neural Networks I, pages 77-90, 1987.
	20	W. Krauth and M. M6zard. Storage capacity of memory networks with binary couplings. J. Phys., 50:3057-3066, 1989.
	21	W. Krauth and M. Opper. Critical storage capacity of the j = +1 neural network. J. Phys. A, 22:L519- L523, 1989.
	22	Y. S. Lashley. The neurophysiology of Lashley; Selected papers of K. S. Lashley. McGraw-Hill, New York, 1960.
	23	W. A. Little. The existence of persistent states in the brain. Mathematical Biosciences, 19:101-119, 1974.
	24	W. A. Little and C. L, Shaw. Analytic study of the memory storage capacity of a neural network. Mathematical Biosciences, 39:281-290, 1978.
	25	G. Mato and N. Parga. Generalization properties of multilayered neural networks. J. Phys. A: Math. Gen., 25:5047-5054, 1992.
	26	W. S. McCulloch and W. H. Pitts. A logical calculus for ideas immanent in nervous activity. Bulletin of Mathematical Bzophys~cs, 5:115-133, 1943.
	27	H. S. Seung, H. Sompolinsky, and N. Tishby. Statistical mechanics of learning from examples. Phys. Rev. A, 45:6056-6091, 1992.
	28	Santosh S. Venkatesh, On learning binary weights for majority functions, Proceedings of the fourth annual workshop on Computational learning theory, p.257-266, August 05-07, 1991, Santa Cruz, California, United States
	29	J. Wendel. A problem in geometric probability. Math. Scand., 11:109-111, 1962.