CFP last date
20 January 2025
Reseach Article

Existence and Learning of Teaching Network for CRNN

by Neeraj Sahu, Avanish Kumar
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 29 - Number 4
Year of Publication: 2011
Authors: Neeraj Sahu, Avanish Kumar
10.5120/3554-4885

Neeraj Sahu, Avanish Kumar . Existence and Learning of Teaching Network for CRNN. International Journal of Computer Applications. 29, 4 ( September 2011), 24-27. DOI=10.5120/3554-4885

@article{ 10.5120/3554-4885,
author = { Neeraj Sahu, Avanish Kumar },
title = { Existence and Learning of Teaching Network for CRNN },
journal = { International Journal of Computer Applications },
issue_date = { September 2011 },
volume = { 29 },
number = { 4 },
month = { September },
year = { 2011 },
issn = { 0975-8887 },
pages = { 24-27 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume29/number4/3554-4885/ },
doi = { 10.5120/3554-4885 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T20:14:54.106997+05:30
%A Neeraj Sahu
%A Avanish Kumar
%T Existence and Learning of Teaching Network for CRNN
%J International Journal of Computer Applications
%@ 0975-8887
%V 29
%N 4
%P 24-27
%D 2011
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Existence and Learning of Teaching Network for Complex Recurrent Neural Network (CRNN) has been discussed in this piece of research. Issues related to the quaternionic neural network have been taken into consideration. In this paper by considering the special class of CRNN for which existence of attractive periodic solution in teaching network has been obtained and theoretical results has been proved, limit cycle, existence and uniqueness have also been discussed. This work has very much significant for several real world applications.

References
  1. T. Nitta, “A solution to the 4-bit parity problem with a single Quaternary Neuron,” Neural information processing – Leters and Reviews, vol.5 no.2, pp.33-39, 2004.
  2. P. Arena, L. Fortuna, G. Muscato, and M. Xibilia, “ Multilayer perceptrons to approximate Quaternion valued functions,” Neural Network vol.10,no.2,pp.335-342,1997.
  3. N. Matsui, T. Isokawa, H. Kusamichi, F. Peper and H. Nishimura, “Quaternion Neural Network with Geometrical Operation,” Journal of Intelligent & Fuzzy System,vol.15, no.3-4,pp. 149-164,2004.
  4. S. Buchholz and G. Sommer, “Quaternionic spinor MLP,” in 8th European Symposium on Artificial Neural Network (ESANN 2000),2000, pp.377-382.
  5. P. Arena, L. Fortuna, G. Muscato, and M.G. Xibilia, “Neural Networks in Multidimensional Domains,” Ser. Lecture Notes in computer Science. Springer –Verlag,1998, vol.234.
  6. H. Kusamichi, T. Isokawa, N. Matsui,Y.Ogawa, and K.Maeda , “A New scheme for Color Night, Vision by Quaternion Neural Network,” In Proceeding of the 2nd International Conference on Autonomous Robots and Agents (ICARA 2004), 2004, pp.101-106.
  7. M.Yoshida, Y.Kuroe and T.Mori, “ Models of hopfields-type Quaternion Neural Networks and their energy function,” International Journal of Neural System, vol.15.no: 1-2, pp.129-135,2005.
  8. 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.
  9. Monotone Dynamical System. Providence, RI: Amer.Math.Soc.,1995.
  10. J. Mallet-Paret and H. Smith, “The Poincare-Bendixson theorem for monotone cyclic feedback system with delay ,” J. Differential Equation, vol.2, pp.376-421,1990.
  11. S.Townley, A. Iichmann, M. G.WeiB, W. Mcclements, A. Ruiz, D. H. Owens, & D. pretzel-Wolters, “Existences and learning of oscillations in recurrent neural networks. IEEE Trans. Neural Network”., vol. 11, no. 1, pp. 205-214. Jan. 2000.
  12. K.S.Narendra A.Annaswamy, Stable Adaptive System. Engelewood Cliffs, N.J:Prentice- Hall,1987.
  13. W. J. Rugh, “Linear system theory,” Englewood cliffs NJ: Prentice-Hall 1996.
Index Terms

Computer Science
Information Sciences

Keywords

Complex Recurrent Neural Network Limit Cycle Learning Systems Periodic Orbits