On convergence properties of pocket algorithm

IEEE Transactions on Neural Networks

Volumn 8, Issue 3, 1997, Pages 623-629

  Muselli, Marco ^a  

^a CNR   (Italy)

Author keywords

Convergence theorems; Neural networks; Optimal learning; Perceptron algorithm; Pocket algorithm; Threshold neuron

Indexed keywords

CONVERGENCE OF NUMERICAL METHODS; ITERATIVE METHODS; OPTIMIZATION; THEOREM PROVING; VECTORS;

POCKET ALGORITHM; THRESHOLD NEURON;

LEARNING ALGORITHMS;

EID: 0031145145     PISSN: 10459227     EISSN: None     Source Type: Journal    
DOI: 10.1109/72.572101     Document Type: Article

References (28)

1. R. P. Lippmann, "Review of neural networks for speech recognition," Neural Computa., vol. 1, pp. 1-38, 1989.
2. L. C. Yann, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, "Backpropagation applied to handwritten zip code recognition," Neural Computa., vol. 1, pp. 541-551, 1989.
3. I. Guyon, V. Vapnik, B. Boser, L. Bottou, and S. A. Solla, "Structural risk minimization for character recognition," in Advances in Neural Information Processing Systems 4, J. E. Moody, S. J. Hanson, and R. P. Lippmann, Eds. San Mateo, CA: Morgan Kaufmann, 1992, pp. 471-479.
4. A. Lapedes and R. Farber, "How neural nets work," in Neural Information Processing Systems, D. Z. Anderson, Ed. New York: Amer. Inst. Physics, 1987, pp. 442-456.
5. G. Cybenko, "Approximation by superpositions of a sigmoidal function," Math. Contr., Signals, Syst., vol. 2, pp. 303-314, 1989.
6. K. Funahashi, "On the approximate realization of continuous mapping by neural networks," Neural Networks, vol. 2, pp. 183-192, 1989.
7. K. Hornik, M. Stinchcombe, and H. White, "Multilayer feedforward networks are universal approximators," Neural Networks, vol. 2, pp. 359-366, 1989.
8. V. N. Vapnik and A. Y. Chervonenkis, "On the uniform convergence of relative frequencies of events to their probabilities," Theory Probability Applicat., vol. 16, pp. 264-280, 1971.
9. V. Vapnik, Estimation of Dependences Based on Empirical Data. New York: Springer-Verlag, 1982.
10. _, "Principles of risk minimization for learning theory," in Advances in Neural Information Processing Systems 4, J. E. Moody, S. J. Hanson, and R. P. Lippmann, Eds. San Mateo, CA: Morgan Kaufmann, 1992, pp. 831-838.
11. V. Vapnik and L. Bottou, "Local algorithms for pattern recognition and dependencies estimation," Neural Computa., vol. 5, pp. 893-909, 1993.
12. J. S. Judd, "Learning in networks is hard," in Proc. 1st Int. Conf Neural Networks, San Diego, CA, 1987, pp. 685-692.
13. A. Blum and R. L. Rivest, "Training a 3-node neural network is NP-complete," Neural Networks, vol. 5, pp. 117-127, 1992.
14. D. E. Rumelhart, G. E. Hinton, and R. J. Williams, "Learning internal representations by error propagation," in Parallel Distributed Processing, D. E. Rumelhart and J. L. McClelland, Eds. Cambridge, MA: MIT Press, 1986, pp. 318-362.
15. J. Hertz, A. Krogh, and R. G. Palmer, Introduction to the Theory of Neural Computation. Reading, MA: Addison-Wesley, 1991.
16. D. G. Luenberger, Introduction to Linear and Nonlinear Programming, Reading, MA: Addison Wesley, 1984.
17. W. H. Press, B. P. Flannery, S. A. Teukolsky, and W. T. Vetterling, Numerical Recipes in C. Cambridge, U.K.: Cambridge Univ. Press, 1988.
18. F. Rosenblatt, Principles of Neurodynamics. Washington, D.C.: Spartan, 1961.
19. M. Minsky and S. Papert, Perceptrons: An Introduction to Computational Geometry. Cambridge, MA: MIT Press, 1969.
20. Y.-C. Ho and R. L. Kashyap, "An algorithm for linear inequalities and its applications," IEEE Trans. Electron. Computers, vol. EC-14, pp. 683-688, 1965.
21. L. G. Khachiyan, "A polinomial algorithm in linear programming," Sov. Math. Doklady, vol. 20, pp. 191-194, 1979.
22. A. J. Mansfield, "Comparison of perceptron training by linear programming and by the perceptron convergence procedure," in Proc. Int. Joint Conf. Neural Networks, Seattle, WA, 1991, pp. II-25-II-30.
23. S. I. Gallant, "Perceptron-based learning algorithms," IEEE Trans. Neural Networks, vol. 1, pp. 179-191, 1990.
24. _, Neural Networks Learning and Expert Systems. Cambridge, MA: MIT Press, 1993.
25. M. Mézard and J.-P. Nadal, "Learning in feedforward layered networks: The tiling algorithm," J. Phys. A, vol. 22, pp. 2191-2203, 1989.
26. M. Frean, "The upstart algorithm: A method for constructing and training feedforward neural networks," Neural Computa., vol. 2, pp. 198-209, 1990.
27. M. Muselli, "On sequential construction of binary neural networks," IEEE Trans. Neural Networks, vol. 6, pp. 678-690, 1995.
28. _, "Simple expressions for success run distributions in Bernoulli trials," to appear in Statist. Probability Lett., 1996.