Learning binary perceptrons perfectly efficiently

Journal of Computer and System Sciences

Volumn 52, Issue 2, 1996, Pages 374-389

  Fang, Shao C ^a   Venkatesh, Santosh S ^a  

^a UNIVERSITY OF PENNSYLVANIA   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

ALGORITHMS; BOOLEAN FUNCTIONS; COMPUTATIONAL COMPLEXITY; INTEGER PROGRAMMING; LEARNING SYSTEMS; RANDOM PROCESSES; VECTORS;

BINARY INTEGER PROGRAMMING; BINARY PERCEPTRON;

NEURAL NETWORKS;

EID: 0030125804     PISSN: 00220000     EISSN: None     Source Type: Journal    
DOI: 10.1006/jcss.1996.0028     Document Type: Article

References (15)

1. E. B. Baum and Y.-D. Lyuu, The transition to perfect generalisation in perceptions, Neural Comput. 3 (1991), 386-401.
2. S. C. Fang, "The Complexity of Learning Binary Perceptons," Ph.D. dissertation, Dept. of Electrical Eng., University of Pennsylvania, 1995.
3. S. C. Fang and S. S. Venkatesh, On the average tractability of binary integer programming and the curious transition to perfect generalisation in learning majority functions, in "Proceedings, 6th ACM Conf. on Computational Learning Theory," pp. 310-316, ACM Press, New York, 1993.
4. S. C. Fang and S. S. Venkatesh, The capacity of Majority Rule, Random Structures and Algorithms, to appear.
5. W. Feller, "An Introduction to Probability Theory and Its Applications," Vol. I, 3rd ed., Wiley, New York, 1968.
6. E. Gardner and B. Derrida, Three unfinished works on the optimal storage capacity of networks, J. Phys. A: Math. Gen. 22 (1989), 1983-1994.
7. M. Garey and D. Johnson, "Computers and Intractability: A Guide to the Theory of NP-Completeness," Freeman, San Francisco, 1979.
8. M. Golea and M. Marchand, On learning perceptrons with binary weights, Neural Comput. 5 (1993), 767-782.
9. G. Györgi, First order transition to perfect generalisation in a neural network with binary synapses, Phys. Rev. A 41 (1990), 7097-7100.
10. W. Köhler, S. Diederich, W. Kinzel, and M. Opper, Learning algorithm for a neural network with binary synapses, Z. Phys. B 78 (1990), 333-342.
11. Y.-D. Lyuu and I. Rivin, Tight bounds on transition to perfect generalisation in perceptrons, Neural Comput. 4 (1992), 854-862.
12. L. Pitt and L. G. Valiant, Computational limitations on learning from examples, J. Assoc. Comput. Mach. 35, No. 4 (1988), 965-984.
13. H. Sompolinsky, N. Tishby, and H. Seung, Learning from examples in large neural networks, Phys. Rev. Lett. 65 (1990), 1683-1686.
14. S. S. Venkatesh, On learning binary weights for majority functions, in "Proceedings, Fourth Workshop on Computational Learning Theory" (L. G. Valiant and M. K. Warmuth, Eds.), Morgan Kaufmann, San Mateo, CA, 1991.
15. S. S. Venkatesh, Directed drift: A new linear threshold algorithm for learning binary weights on-line, J. Comput. Systems Sci. 46, No. 2 (1993), 198-217.