Abdul-Wahed Salman, M. (2008). ADAPTIVE LEARNING RATE VERSUS RESILIENT BACKPROPAGATION FOR NUMERAL RECOGNITION. , 2(1), 94-105. doi: 10.37652/juaps.2008.15445
Muntaser Abdul-Wahed Salman. "ADAPTIVE LEARNING RATE VERSUS RESILIENT BACKPROPAGATION FOR NUMERAL RECOGNITION". , 2, 1, 2008, 94-105. doi: 10.37652/juaps.2008.15445
Abdul-Wahed Salman, M. (2008). 'ADAPTIVE LEARNING RATE VERSUS RESILIENT BACKPROPAGATION FOR NUMERAL RECOGNITION', , 2(1), pp. 94-105. doi: 10.37652/juaps.2008.15445
Abdul-Wahed Salman, M. ADAPTIVE LEARNING RATE VERSUS RESILIENT BACKPROPAGATION FOR NUMERAL RECOGNITION. , 2008; 2(1): 94-105. doi: 10.37652/juaps.2008.15445

ADAPTIVE LEARNING RATE VERSUS RESILIENT BACKPROPAGATION FOR NUMERAL RECOGNITION

Journal of University of Anbar for Pure Science
Article 9, Volume 2, Issue 1, 2008, Pages 94-105    PDF (413.04 K)
Document Type: Research Paper
DOI: 10.37652/juaps.2008.15445
Author
Muntaser Abdul-Wahed Salman*
University of Alanbar- College of Computer
Abstract
Two types of neural networks learning algorithms were created, trained, tested, and evaluated in an effort to find the appropriate neural network training method for use in numeral recognition problem. The purpose of this study was to compare the training speeds of two neural networks Backpropagation learning algorithms (Adaptive learning rate and Resilient) when exposed to ten number recognition data sets. Each algorithm was trained using ten data sets as a basic set (Boolean value), and a complex (noisy) set. The trials conducted indicated a significant difference between the two algorithms in the basic data set, with the Resilient training algorithm the neural network trained faster.The creation, training, and testing of each neural network was done using the MathWorks software package MATLAB which contains a “Neural Network Toolbox” that facilitates rapid creation, training, and testing of neural networks. MATLAB was chosen to use for learning algorithm development because this toolbox would save an enormous amount programming effort.
Keywords
ADAPTIVE; LEARNING RATE; BACKPROPAGATION; NUMERAL RECOGNITION
References
 

  1. Ben, K. and Patrick S. (1996). An Introduction to Neural Networks. Eighth Edition. November 1996.
  2. Fahlman, S. (1988). An Empirical Study of Learning Speed in Back-Propagation Networks. Carnegie Mellon: CMU-CS-88-162
  3. Firas, H. (2000). Handwritten Numeral Recognition Using Neural Networks. EE368, Stanford University. 27 May, 2000. Available at http://scien.stanford.edu/class/ee368/projects2000/project/node1.html.
  4. Goss, N. J. (2000). Resilient Backpropagation versus Quickprop for Character Recognition in Neural Networks.
  5. Howard, D. and Mark, B. (2002). Neural Network Toolbox for use with Matlab. 'User's Guide Version 4'. July 2002.
  6. Jacek, M. Zurada (1996). Introduction to Artificial Neural Systems.
  7. Klimis, S. (2000). Hand Gesture Recognition Using Neural Networks
  8. Riedmiller, M. (1994). Rprop - Description and Implementation Details Technical Report. University of Karlsruhe: W-76128 Karlsruhe.
  9. Riedmiller, M. (1994). Advanced Supervised Learning in Multi-layer Perceptrons From Backpropagation to Adaptive Learning Algorithms. University of Karlsruhe: W-76128 Karlsruhe.
  10. Riedmiller, M. and H. Braun 1993. A direct adaptive method for faster backpropagation learning: The RPROP algorithm. Proceedings of the IEEE International Conference on Neural Networks, San Francisco, 1993.
  11. Sang-W. M. and Seong-G. K. (2002). Pattern Recognition with Block-based Neural Networks. 0-7803-7278-6/2002 ©2002 IEEE.
Statistics
Article View: 401
PDF Download: 171


Journal Management System. Powered by iJournalPro.com