Neural Network Structure Optimization In Pattern Recognition

Piotr Czekalski, Karol Łyp

Abstract


This paper presents the analysis of the feed-forward, multilayer feed-forward network and its structure and parameters on pattern recognition effectiveness. The detailed, experimental results in Latin alphabet recognition with respect to the number of network layers, activation function and its parameters, number of connections between layers and output coding is discussed.


Keywords


neural networks; pattern recognition; OCR; optimization

Full Text:

PDF

References


Ahmmed S., Abdullah-Al-Mamun K., Islam M.: A novel algorithm for designing three layered artificial neural networks. Int. J. Soft Computing, Vol. 2, No. 3, 2007, p. 450÷458.

Armstrong A.: Google's Deep Learning - Speech Recognition. [@:] http://www.i-programmer.info/news/105-artificial-intelligence/4638-googles-deep-learning-speech-recognition.html, I Programmer, 2012.

Chester, D. L.: Why Two Hidden Layers are Better than One. IJCNN-90-WASH-DC, Lawrence Erlbaum, Vol. 1, 1990, p. 265÷268.

Choudhary A., Rishi R.: Improving the Character Recognition Efficiency of Feed Forward Bp Neural Network, Int. J. of Computer Science & Information Technology, Vol. 3, No. 1, 2011.

Emmerson M. D., Damper R. I.: Determining and improving the fault tolerance of multi layer perceptrons in a pattern-recognition application., IEEE Trans. Neural Netw., Vol. 4, 1993, p. 788÷793.

Hammerstrom D.: Neural networks at work. IEEE Spectrum, Vol. 30, No. 6, 1993.

Huang S.C., Huang Y.F.: Bounds on the number of hidden neurons in multilayer perceptrons. IEEE Trans. Neural. Netw., Vol. 2, 1991, p. 47÷55.

Henrique M., Lima L., Seborg E.: Model structure determination in neural network models, Chem. Eng. Sci., Vol. 55, 2000, p. 5457÷5469.

Kamruzzaman J., Aziz S. M.: A Note on Activation Function in Multilayer Feedforward Network, IEEE Xplore, 2002.

Koerich A. L., Sabourin R., Suen C. Y.: Large vocabulary off-line handwriting recognition: A survey. Pattern Analysis and Applications, Vol. 6, No. 2, 2003, p. 97÷121.

Kriesel D.: A brief introduction to neural networks, [@:] http://www.dkriesel.com/en/science/neural_networks, 2007.

Kröse B.,Van der Smagt P.: An introduction to neural networks. University of Amsterdam, 1993.

Reitermanova Z.: Feedforward Neural Networks – Architecture Optimization and Knowledge Extraction. Proc. WDS’08, Vol. 1, 2008, p. 159÷164.

Rojas R.: Neural Networks – A Systematic Introduction. Springer-Verlag, Berlin, New-York 1996.

Rutkowski L.: Metody i techniki sztucznej inteligencji: inteligencja obliczeniowa. Wydawnictwo Naukowe PWN, Warszawa 2005.

Steinherz T., Rivlin E., Intrator N.: Off-line cursive script word recognition – A survey. International Journal of Document Analysis and Recognition, Vol. 2, 1999, p. 90÷110.

Tadeusiewicz R.: Odkrywanie właściwości sieci neuronowych przy użyciu programów w języku C#. Polska Akademia Umiejętności, 2007.

Zięba M.: Multistage Neural Networks: Multistage Neural Networks for Solving Pattern Recognition Problems. LAP LAMBERT Academic Publishing, 2010.




DOI: http://dx.doi.org/10.21936/si2014_v35.n4.703