CFP last date
20 December 2024
Call for Paper
January Edition
IJCA solicits high quality original research papers for the upcoming January edition of the journal. The last date of research paper submission is 20 December 2024

Submit your paper
Know more
The week's pick
Responsive image
SFLA-Based Line Balancing and Task Optimization in Master-Slave Controlled Hanger Transportation Systems for Garment Production

Duc Hoang Nguyen
Random Articles
Reseach Article

Differential learning algorithm for Artificial Neural Networks

by Manjunath R, Shyam vasudev, Narendranath Udupa
journal cover thumbnail

International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 1 - Number 18
Year of Publication: 2010
Authors: Manjunath R, Shyam vasudev, Narendranath Udupa
10.5120/381-571

Manjunath R, Shyam vasudev, Narendranath Udupa . Differential learning algorithm for Artificial Neural Networks. International Journal of Computer Applications. 1, 18 ( February 2010), 65-70. DOI=10.5120/381-571

@article{ 10.5120/381-571,
author = { Manjunath R, Shyam vasudev, Narendranath Udupa },
title = { Differential learning algorithm for Artificial Neural Networks },
journal = { International Journal of Computer Applications },
issue_date = { February 2010 },
volume = { 1 },
number = { 18 },
month = { February },
year = { 2010 },
issn = { 0975-8887 },
pages = { 65-70 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume1/number18/381-571/ },
doi = { 10.5120/381-571 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-06T19:46:43.601017+05:30
%A Manjunath R
%A Shyam vasudev
%A Narendranath Udupa
%T Differential learning algorithm for Artificial Neural Networks
%J International Journal of Computer Applications
%@ 0975-8887
%V 1
%N 18
%P 65-70
%D 2010
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Artificial Neural Networks (ANN) are extremely useful to relate the nonlinearly depending outputs with the inputs. Various architectures are available for the ANNs to speedup the training period and reduce the square error. In this paper, new classes of neural networks with differential feedback are presented. The different orders of differential feed back form a manifold of hyperplanes. Interesting properties of this differentially fed ANN (DANN) are derived through these hyperplanes.

References
  1. Manjunath.R and K.S.Gurumurthy,2002. System design using differentially fed Artificial Neural networks, TENCON'02.
  2. Aarts, E.H.L. and Korst, J.H.M., 1989. Simulated Annealing and Boltzmann Machines, Chichester: Wiley.
  3. S.Amari , 1995. Information Geometry of the EM and em algorithms for neural networks, Neural networks, 8,No.9.
  4. Amari.s., 1982. Differential geometry of curved exponential families -curvatures and Information loss. Annals of statistics.
  5. Amari.s. Information Geometry of neural networks-New Bayesian Duality theory-
  6. S.Amari,1998. Natural gradient works efficiently in learning, neural computation 10, pp..251-276
  7. S.Amari and H.Nagaoka,2000. Methods of information geometry,AMS and Oxford university press.
  8. Amari,1995. Information geometry of EM and em algorithms for neural networks, Neural networks 8(9),pp. 1379-1408
  9. Amari.s, 1990.mathematical foundations of neurocomputing, Proceedings of IEEE, 78, pp 1446-1463
  10. D.J.C.Mac Kay, 1992.A practical Bayesian framework for back propagation networks Neural computation 4,pp. 448-472
  11. Radford Neal, 1996. Bayesian learning in neural networks springer verlag.
  12. D.J.C. MacKay. 1992.The evidence framework applied to classification networks.Neural computation, 4, pp720-736
  13. D.J.C.MacKay,1992. A practical Bayesian framework for backpropagation networks.Neural computation, 4, pp.448-472
  14. Zhu, H. and Rohwer, R. 1995. Bayesian invariant measurements of generalisation for continuous distributions. Technical Report NCRG/4352,Aston University. ftp://cs.aston.ac.uk/neural/zhuh/ continuous .ps.Z.
  15. Rao, C. R. 1962. Efficient estimates and optimum inference procedures in large samples J. R. Statist. Soc., B, 24, pp.46-72
  16. Peter Meinicke and Helge Ritter.1999. ,Resolution based complexity control for Gaussian mixture models. Technical report, Faculty of Technology, University of Bielefeld.
  17. McKenzie, P. and Alder. M. , 1994. Initializing the EM algorithm for use in Gaussian mixture modelling. In Gelsema, E. S. and Kanal, L. N., editors, Pattern Recognition in Practice IV, Amsterdam: Elsevier., pp.91-105
  18. M.Frazier and B.Jawerth. 1985.Decomposition of Besov spaces Indiana univ. of Maths journal 34(4),pp.777-779
  19. S.Mallat and W.L.Hwang, 1991. Singularity detection and processing with wavelets. Preprint Courant Institute of Mathematical sciences, New York University.
  20. B. Jawerth and G. peters,1993. Wavelets on non smooth sets of Rn. Reprint.
Index Terms

Computer Science
Information Sciences

Keywords

Adaptive control Neural networks Differential feedback Multiresolution

Powered by PhDFocusTM