Modified Mean Square Error Algorithm with Reduced Cost of Training and Simulation Time for Character Recognition in Backpropagation Neural Network

Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 247)

Abstract

Neural Network concept is based on “Learn by example”. Mean square error function is the basic performance function which affects the network directly. Reducing of such error will result in an efficient system. The paper proposes a modified mean squared error value while training Backpropagation (BP) neural networks. The new cost function is referred as Arctan mean square error (AMSE).The formula computed prove that the modification of MSE is optimal in the sense of reducing the value of error for an asymptotically large number of statistically independent training data patterns. The results shows improved network with reduced error value along with increment in performance consequently.

Keywords

Backpropagation algorithm Mean square error algorithm neural network 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Wilamowski, B.M., Iplikci, S., Kaynak, O., ÖnderEfe, M.: An Algorithm for Fast Convergence in Training Neural, 0-7803-7044-9/01/$10.00 © (2001) IEEEGoogle Scholar
  2. 2.
    Rady, H.: Reyni’s Entropy and Mean Square Error for Improving the Convergence of Multilayer Backpropagation Neural Networks: A Comparative. Study117905-8282 IJECS-IJENS 11(5) (October 2005)Google Scholar
  3. 3.
    Osman, H., Blostan, S.D.: New cost function for Backpropagation neural network with application to SAR imagery classification,K7l396Google Scholar
  4. 4.
    Finnie, G.R., Wittig, G.E.: A Comparison of Software Effort Estimation Techniques: Using Function Points with Neural Networks, Case Based Reasoning and Regression Models. Journal of Systems and Software 39, 281–289 (1997)CrossRefGoogle Scholar
  5. 5.
    Finnie, G.R., Wittig, G.E.: AI Tools for Software Development Effort Estimation. In: Proceedings of the International Conference on Software Engineering: Education and Practice, SEEP 1996 (1996)Google Scholar
  6. 6.
    Srinivasan, K., Fisher, D.: Machine Learning Approaches to Estimating Software Development Effort. IEEE Transactions on Software Engineering 21 (February 1995)Google Scholar
  7. 7.
    Arora, S., Bhattacharjee, D., Nasipuri, M., Malik, L., Kundu, M., Basu, D.K.: Performance Comparison of SVM and ANN for Handwritten Devnagari Character Recognition. IJCSI International Journal of Computer Science Issues 7(3) (May 2010)Google Scholar
  8. 8.
    Devireddy, S.K., Rao, S.A.: Hand written character recognition using backpropagation network. Journal of Theoretical and Applied Information Technology, JATIT (2005 - 2009)Google Scholar
  9. 9.
    Shahi, M., Ahlawat, A.K., Pandey, B.N.: Literature Survey on Offline Recognition of Handwritten Hindi Curve Script Using ANN Approach. International Journal of Scientific and Research Publications 2(5) (May 2012) ISSN 2250-3153Google Scholar
  10. 10.
    Garg, N., Kaur, S.: Improvement in Efficiency of Recognition of Handwritten Gurumukhi Script. IJCST 2(3) (September 2011)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Sapna Singh
    • 1
  • Daya Shankar Singh
    • 1
  • Shobhit Kumar
    • 2
  1. 1.Computer Science and Engineering DepartmentMadan Mohan Malaviya Engineering CollegeGorakhpurIndia
  2. 2.Information Technology DepartmentManyawar Kanshiram Institute of Engineering & Information TechnologyAkbarpurIndia

Personalised recommendations