Research Article

Analysis of Equilibria of a Recurrent Neural Network involving Transcendental Function

by  Neeraj Sahu, A. K. Verma
journal cover
International Journal of Applied Information Systems
Foundation of Computer Science (FCS), NY, USA
Volume 4 - Issue 5
Published: October 2012
Authors: Neeraj Sahu, A. K. Verma
10.5120/ijais12-450700
PDF

Neeraj Sahu, A. K. Verma . Analysis of Equilibria of a Recurrent Neural Network involving Transcendental Function. International Journal of Applied Information Systems. 4, 5 (October 2012), 6-12. DOI=10.5120/ijais12-450700

                        @article{ 10.5120/ijais12-450700,
                        author  = { Neeraj Sahu,A. K. Verma },
                        title   = { Analysis of Equilibria of a Recurrent Neural Network involving Transcendental Function },
                        journal = { International Journal of Applied Information Systems },
                        year    = { 2012 },
                        volume  = { 4 },
                        number  = { 5 },
                        pages   = { 6-12 },
                        doi     = { 10.5120/ijais12-450700 },
                        publisher = { Foundation of Computer Science (FCS), NY, USA }
                        }
                        %0 Journal Article
                        %D 2012
                        %A Neeraj Sahu
                        %A A. K. Verma
                        %T Analysis of Equilibria of a Recurrent Neural Network involving Transcendental Function%T 
                        %J International Journal of Applied Information Systems
                        %V 4
                        %N 5
                        %P 6-12
                        %R 10.5120/ijais12-450700
                        %I Foundation of Computer Science (FCS), NY, USA
Abstract

In this paper we present four node recurrent neural networks system with three weight parameters. This closed recurrent neural network generates a limit cycle. In this system for which the equation of equilibria involves transcendental function tan h(X) and its iterates. The network is shown to trains a desired periodic signal by varying weights.

References
  • A. Ruiz, D. H. Owens, and S. Townley, "Existence, learning, and replication of periodic motions in recurrent neural network," IEEE Trans. Neural Network. Vol. 9. no 4, pp 651- 661, jul. 1998.
  • Bo. Gao, and Weinian. Zhang, "Equilibria and their bifurcation in a recurrent neural network involving iterates of a transcendental function," IEEE Trans. Neural Networks. Vol. 19 No. 5. Pp. 782-794, May 2008.
  • D. Marr. and T. Poggio. Cooperative computation of stereo disparity, sci. , vol 194 pp 283 –287, 1976.
  • J. K. Hale, Theory of function differential equations 2nd ed. Applied mathematical sciences, vol. 3 Springer , new York, 1977.
  • J. J. Hofield, Neurons with graded response have collective computational properties like those of two state neurons proceeding of the national academy of sciences of the United States of America 81 (1984) no . 10 3088- 3092.
  • J. L. McClelland. D. E. Rumclhart. and G. E. Hinton. "The appeal of parallel distributed processing. " in Rinehart. D. E. , McClelland. J. L. , and the PDP research group Eds. , parallel distributed processing explorations in microstructure of cognition volume l. Foundations Cambridge MA:MIT Press 1986 .
  • S. Hasting, J. Tyson, and D. Webster, "Existence of periodic solution for negative feedback cellular control system," J. Differential Equations, vol. 25, pp. 39-64,1977.
  • R. Szeliski. "cooperative algorithms for solving random dot stereo grams" , Carnegie Mellon Univ. Tech Rep CMU-CS –86-133,1986.
  • Yingguo Li "Stability and Bifurcation Analysis of a Three- Dimensional Recurrent Neural Network with Time Delay" Hindawi Publishing Corporation Journal of Applied Mathematics. Volume 2012 Article ID 357382, 13 pages doi:10. 1155/2012/357382
  • Yujiao Huang, Huaguang Zhang, Zhanshan Wang and Mo Zhao. "Stability Analysis of Multiple Equilibria for Recurrent Neural Networks," Advances in neural network-ISNN 2012. Lecture notes in computer science Volume 7367, 2012, pp196-205.
Index Terms
Computer Science
Information Sciences
No index terms available.
Keywords

Neural network limit cycle nonlinear dynamics learning systems transcendental function equilibrium

Powered by PhDFocusTM