Exponential transients in continuous-time Liapunov systems

Theoretical Computer Science

Volumn 306, Issue 1-3, 2003, Pages 353-372

  Šíma, Jiří ^a   Orponen, Pekka ^b  

^a INSTITUTE OF COMPUTER SCIENCE   (Czech Republic)

^b AALTO UNIVERSITY   (Finland)

Author keywords

Continuous time; Convergence time; Dynamical system; Hopfield network; Liapunov function

Indexed keywords

COMPUTER SIMULATION; CONVERGENCE OF NUMERICAL METHODS; FUNCTIONS; LYAPUNOV METHODS;

DYNAMIC SYSTEMS;

NEURAL NETWORKS;

EID: 0041888472     PISSN: 03043975     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0304-3975(03)00310-4     Document Type: Article

References (16)

1. Ben-Hur A., Siegelmann H.T., Fishman S. A theory of complexity for continuous time systems. J. Complexity. 18:2002;51-86.
2. Cohen M.A., Grossberg S. Absolute stability of global pattern formation and parallel memory storage by competitive neural networks. IEEE Trans. Systems Man Cybernet. 13:1983;815-826.
3. Golden R.M. Mathematical Methods for Neural Network Analysis and Design. 1996;MIT Press, Cambridge, MA.
4. Goles E., Martínez S. Exponential transient classes of symmetric neural networks for synchronous and sequential updating. Complex Systems. 3:1989;589-597.
5. Gori M., Meer K. A step towards a complexity theory for analog systems. Math Logic Quart. 48:2002;45-58.
6. Haykin S. Neural Networks: A Comprehensive Foundation. 2nd Ed:1999;Prentice-Hall, Upper Saddle River, NJ.
7. Hopfield J.J. Neurons with graded response have collective computational properties like those of two-state neurons. Proc. Nat. Acad. Sci. 81:1984;3088-3092.
8. Hopfield J.J., Tank D.W. "Neural" computation of decisions in optimization problems. Biol. Cybernet. 52:1985;141-152.
9. C. Moore, Finite-dimensional analog computers: flows, maps, and recurrent neural networks, in: Proc. 1st Internat. Conf. on Unconventional Models of Computation, Auckland, January 1998, Springer-Verlag, Berlin, 1998, pp. 59-71.
10. Numerical Algorithms Group, Fortran library routine D02PCF, 2002, Manual electronically available via http://www.nag.co.uk/numeric/fl/manual/pdf/D02/d02pcf.pdf .
11. Orponen P. A survey of continuous-time computation theory. Du D.-Z., Ko K.-I. Advances in Algorithms, Languages, and Complexity. 1997;209-224 Kluwer Academic Publishers, Dordrecht.
12. Siegelmann H.T. Neural Networks and Analog Computation: Beyond the Turing Limit. 1999;Birkhäuser, Boston, MA.
13. J. Šíma, P. Orponen, Computing with continuous-time Liapunov systems, in: Proc. 33rd Ann. ACM Symp. on Theory of Computing, (Crete, July 2001), Association for Computing Machinery, New York, NY, 2001, pp. 722-731.
14. J. Šíma, P. Orponen, Exponential transients in continuous-time symmetric Hopfield nets, in: Proc. 11th Internat. Conf. on Artificial Neural Networks, Vienna, August 2001, Lecture Notes on Computer Science, vol. 2130, Springer-Verlag, Berlin, 2001, pp. 806-813.
15. Šíma J., Orponen P., Antti-Poika T. On the computational complexity of binary and analog symmetric Hopfield nets. Neural Comput. 12:2000;2965-2989.
16. H.M. Stoll, L.-S. Lee, A continuous-time optical neural network, in: Proc. IEEE Internat. Conf. on Neural Networks, (San Diego, CA, July 1998), Vol. II, 1988, pp. 373-384.