A Learning and Forgetting Algorithm in Associative Memories: Results Involving Pseudo-Inverses

IEEE Transactions on Circuits and Systems

Volumn 38, Issue 10, 1991, Pages 1193-1205

  Yen, Gune ^a   Michel, Anthony N ^a  

^a UNIVERSITY OF NOTRE DAME   (United States)

Author keywords

[No Author keywords available]

Indexed keywords

EID: 0001449933     PISSN: 00984094     EISSN: None     Source Type: Journal    
DOI: 10.1109/31.97539     Document Type: Article

References (26)

1. J. J. Hopfield, “Neural networks and physical systems with emergent collective computational abilities,” in Proc. Nat. Acad. Sciences, vol. 79, pp. 2554–2558, Apr. 1982.
2. _, “Neurons with graded response have collective computational properties like those of two-state neurons,” in Proc. Nat. Acad. Sciences, vol. 81, pp. 3088–3092, May 1984.
3. L. Personnaz, I. Guyon, and G. Dreyfus, “Information storage and retrieval in spin-glass like neural networks,” J. Physique Letters, vol. 46, pp. L359-356, Apr. 1985.
4. _, “Collective computational properties of neural networks: New learning mechanisms,” Phys. Rev., A, vol. 34, pp. 4217–4228, Nov. 1986.
5. J. H. Li, A. N. Michel, and W. Porod, “Qualitative analysis and synthesis of a class of neural networks,” IEEE Trans. Circuits Syst., vol. 35, pp. 976–986, Aug. 1988.
6. _, “Analysis and synthesis of a class of neural networks: Variable structure systems with infinite gains,” IEEE Trans. Circuits Syst., vol. 36, pp. 713–731, May 1989.
7. _, “Analysis and synthesis of a class of neural networks: Linear systems operating on a closed hypercube,” IEEE Trans. Circuits Syst., vol. 36, pp. 1405–1422, Nov. 1989.
8. A. N. Michel, J. Si, and G. Yen, “Analysis and synthesis of a class of discrete-time neural networks described on a closed hypercube,” IEEE Trans. Neural Networks, vol. 2, pp. 32–46, Jan. 1991.
9. A. N. Michel, J. A. Farrell, and W. Porod, “Qualitative theory of neural networks,” IEEE Trans. Circuits Syst., vol. 36, pp. 229–243, Feb. 1989.
10. J. A. Farrell and A. N. Michel, “A synthesis procedure for Hopfield's continuous-time associative memory,” IEEE Trans. Circuits Syst., vol. 37, pp. 877–884, July 1990.
11. A. N. Michel, J. A. Farrell, and H. F. Sun, “Analysis and synthesis techniques for Hopfield type synchronous discrete neural networks with application to associative memory,” IEEE Trans. Circuits Syst., vol. 37, pp. 1356–1366, Nov. 1990.
12. A. N. Michel and J. A. Farrell, “Associative memories via artificial neural networks,” IEEE Contr. Syst. Mag., vol. 10, pp. 6–17, Apr. 1990.
13. Y. S. Abu-Mostafa and J. M. St. Jacques, “Information capacity of the Hopfield model,” IEEE Trans. Inform. Theory, vol. 31, pp. 461–464, July 1985.
14. J. J. Hopfield, D. I. Feinstein, and R. E. Palmer, “‘Unlearning’ has a stability effect in collective memories,” Nature, vol. 304, pp. 158–159, July 1983.
15. A. N. Michel and R. K. Miller, Qualitative Analysis of Large-Scale Dynamical Systems. New York: Academic, 1977.
16. R. K. Miller and A. N. Michel, Ordinary Differential Equations. New York: Academic, 1982.
17. A. N. Michel and R. K. Miller, “On stability preserving mappings,” IEEE Trans. Circuits Syst., vol. 30, pp. 671–680, Sept. 1983.
18. T. N. E. Greville, “The pseudoinverse of a rectangular or singular matrix and its application to the solution of systems of linear equations,” SIAM Review, vol. 1, pp. 38–43, Jan. 1959.
19. _, “Some applications of the pseudoinverse of a matrix,” SIAM Review, vol. 2, pp. 15–22, Jan. 1960.
20. A. Albert, Regression and the Moore - Penrose Pseudo-Inverse. New York: Academic, 1972.
21. A. Ben-Israel and T. N. E. Greville, Generalized Inverses — Theory and Applications. New York: Wiley, 1974.
22. W. H. Press, B. P. Flannery, S. A. Teukolsky, and W. T. Vetterling, Numerical Recipes — The Art of Scientific Computing. Cambridge: Cambridge University Press, 1986.
23. R. J. McEliece, E. C. Posner, E. R. Rodemich, and S. S. Venkatesh, “The capacity of the Hopfield associative memory,” IEEE Trans. Inform. Theory, vol. 33, pp. 461–482, July 1987.
24. A. Kuh and B. W. Dickinson, “Information capacity of associative memories,” IEEE Trans. Inform. Theory, vol. 35, pp. 59–68, Jan. 1989.
25. E. Marom, “Associative memory neural networks with concatenated vectors and nonzero diagonal terms,” Neural Networks, vol. 3, pp. 311–318, 1990.
26. L. Personnaz, I. Guyon, G. Dreyfus, and G. Toulouse, “A biological constrained learning mechanism in networks of formal neurons,” J. Statistical Phys., vol. 43, pp. 411–422, May 1986.