Journal of the Korean Society for Industrial and Applied Mathematics

Korean Society for Industrial and Applied Mathematics (한국산업응용수학회)
권호 표지
DOI QR코드

DOI QR Code

A MODIFIED EXTENDED KALMAN FILTER METHOD FOR MULTI-LAYERED NEURAL NETWORK TRAINING

  • KIM, KYUNGSUP (DEPARTMENT OF COMPUTER ENGINEERING, CHUNGNAM NATIONAL UNIVERSITY) ;
  • WON, YOOJAE (DEPARTMENT OF COMPUTER ENGINEERING, CHUNGNAM NATIONAL UNIVERSITY)
  • Received : 2018.05.16
  • Accepted : 2018.06.11
  • Published : 2018.06.25
Download PDF
⟨ Previous Next ⟩

Abstract

This paper discusses extended Kalman filter method for solving learning problems of multilayered neural networks. A lot of learning algorithms for deep layered network are sincerely suffered from complex computation and slow convergence because of a very large number of free parameters. We consider an efficient learning algorithm for deep neural network. Extended Kalman filter method is applied to parameter estimation of neural network to improve convergence and computation complexity. We discuss how an efficient algorithm should be developed for neural network learning by using Extended Kalman filter.

Keywords

References

  1. Ben Cherif Aissa and Chouireb Fatima. Neural Networks Trained with Levenberg-Marquardt-Iterated Ex- tended Kalman Filter for Mobile Robot Trajectory Tracking. Journal of Engineering Science and Technology Review, 10(4):191-198, 2017.
  2. A. N. Chernodub. Training Neural Networks for classification using the Extended Kalman Filter: A compar- ative study. Optical Memory and Neural Networks, 23(2):96-103, 2014. https://doi.org/10.3103/S1060992X14020088
  3. Mohinder S. Grewal and Angus P. Adnrews. Kalman filtering - theory and practice using matlab. John Wiley & Sons, Inc., 2008.
  4. Simon Haykin. Neural Networks and Learning Machines. 1999.
  5. SS Haykin. Kalman Filtering and Neural Networks. 2001.
  6. Y. Iiguni, H. Sakai, and H. Tokumaru. A real-time learning algorithm for a multilayered neural network based on the extended Kalman filter. IEEE Transactions on Signal Processing, 40(4):959-966, apr 1992. https://doi.org/10.1109/78.127966
  7. K.S. Narendra and K Parthasarathy. Identification and control of dynamical systems using neural networks. IEEE Transactions on Neural Networks, 1(1):4-27, 1990. https://doi.org/10.1109/72.80202
  8. Raul Rojas. Neural Networks. Springer, 1996.
  9. David E Rumelhart, Geoffrey E Hinton, and R J Williams. Learining Internal Representations by Error Propagation, 1986.
  10. Shared Singhal and Lance Wu. Training Multilayer Perceptrons with the Extended Kalman Algorithm. Nips, pages 133-140, 1988.
  11. Keigo Watanabe, Toshio Fukuda, and Spyros G. Tzafestas. Learning algorithms of layered neural networks via extended kalman filters. International Journal of Systems Science, 22(4):753-768, 1991. https://doi.org/10.1080/00207729108910654
  12. Keigo Watanabe and Spyros G. Tzafestas. Learning Algorithms for Neural Networks with the Kalman Filters. Journal of lntelligent and Robotic Systems, 3:305-319, 1990. https://doi.org/10.1007/BF00439421
  13. Hao Yu and Bogdan Wilamowski. LevenbergMarquardt Training. 2011.