The magnitude of the diagonal elements in neural networks

Neural Networks

Volumn 10, Issue 3, 1997, Pages 499-504

  De Wilde, Philippe ^a  

^a IMPERIAL COLLEGE LONDON   (United Kingdom)

Author keywords

associative memory; capacity; diagonal; hysteresis; neural networks; self coupling; self feedback; spurio us patterns

Indexed keywords

ASSOCIATIVE STORAGE; COMPUTER SIMULATION; LEARNING SYSTEMS; MATRIX ALGEBRA; STATISTICS;

CAPACITY; DIAGONAL ELEMENTS; SELF COUPLING; SELF FEEDBACK; SPURIOUS PATTERNS;

NEURAL NETWORKS;

ARTICLE; ARTIFICIAL NEURAL NETWORK; MEMORY; PRIORITY JOURNAL;

EID: 0031128189     PISSN: 08936080     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0893-6080(96)00094-9     Document Type: Article

References (19)

1. Abramowitz, M., & Stegun, I.A. (1970). Handbook of mathematical functions. New York: Dover.
2. Cheung P.Y.K., Ferrari A., De Wilde P., Benyon-Tinker G. A neural network processor - a vehicle for teaching system design. IEE Proceedings - G. 139:1992;244-248.
3. De Wilde, P. (1989). A Marquardt learning algorithm for neural networks, In A.M. Barbé (Ed.), Proceedings of the Tenth Symposium on Information Theory in the Benelux, (pp. 51-57). Enschede, The Netherlands: Werkgemeenschap voor Informatie - en Communicatietheorie.
4. De Wilde P. Class of Hamiltonian neural networks. Physical Review E. 47:1993;1392-1396.
5. El Leithy, N., & Newcomb, R.W. (1988). Hysteresis in neural-type circuits, In IEEE International Symposium on Circuits and Systems: Proceedings, (pp. 993-996). IEEE.
6. Goles, E., & Martinez, S. (1990). Neural and automata networks. Dordrecht: Kluwer.
7. Hertz, J., Krogh, A., & Palmer, R.G. (1991). Introduction to the theory of neural computation. Redwood City, CA: Addison Wesley.
8. Kamp, Y., & Hasler, M. (1990). Recursive neural networks for associative memory. Chichester: Wiley.
9. Kanter I., Sompolinsky H. Associative recall of memory without errors. Physical Review A. 35:1987;380-392.
10. Keeler J.D., Pichler E.E., Ross J. Noise in neural networks - thresholds, hysteresis, and neuromodulation of signal-to-noise. Proceedings of the National Academy of Science of the USA. 86:1988;1712-1716.
11. Kohli C.K., Ajmera R.C., Kiruthi G., Newcomb R.W. Hysteretic system for neural-type circuits. Proceedings of the IEEE. 69:1981;285-287.
12. Levendovsky, J., Mommaerts, W., & Van der Meulen, E.C. (1991). Neural networks with hysteresis type of nonlinearity exhibit global optimization property, In A. Prieto, (Ed.), Lecture Notes in Computer Science Vol. 540, (pp. 62-68). Berlin: Springer-Verlag.
13. Li J.H., Michel A.N., Porod W. Qualitative analysis and synthesis of a class of neural networks. IEEE Transactions on Circuits and Systems. CAS-35:1988;976-985.
14. Marom E. Associative memory neural networks with concatenated vectors and nonzero diagonal terms. Neural Networks. 3:1990;311-318.
15. McEliece R.J., Posner E.C., Rodemich E.R., Venkatesh S.S. The capacity of the Hopfield associative memory. IEEE Transactions on Information Theory. IT-33:1987;461-482.
16. Ohta M., Anzai Y., Yoneda S., Ogihara A. A theoretical analysis of neural networks with nonzero diagonal elements. IEICE Transactions on Fundamentals of Electronics Communications and Computer Sciences. E76-A:1993;284-291.
17. Pollard, D. (1984). Convergence of stochastic processes. New York: Springer-Verlag.
18. Wang L.P., Ross J. Synchronous neural networks of nonlinear threshold elements with hysteresis. Proceedings of the National Academy of Sciences of the USA. 87:1990;988-992.
19. Yanai H., Sawada Y. Associative memory network composed of neurons with hysteretic property. Neural Networks. 3:1990;223-228.