Influence of graphical weights’ interpretation and filtration algorithms on generalization ability of neural networks applied to digit recognition

In this paper, the method of the graphical interpretation of the single-layer network weights is introduced. It is shown that the network parameters can be converted to the image and their particular elements are the pixels. For this purpose, weight-to-pixel conversion formula is used. Moreover, new weights’ modification method is proposed. The weight coefficients are computed on the basis of pixel values for which image filtration algorithms are implemented. The approach is applied to the weights of three types of the models: single-layer network, two-layer backpropagation network and the hybrid network. The performance of the models is then compared on two independent data sets. By means of the experiments, it is presented that the adjustment of the weights to new values decreases test error value compared to the error obtained for initial set of weights.

[1]  Yann LeCun,et al.  Handwritten zip code recognition with multilayer networks , 1990, [1990] Proceedings. 10th International Conference on Pattern Recognition.

[2]  Zheng-Xing Sun,et al.  User-Independent Online Handwritten Digit Recognition , 2006, 2006 International Conference on Machine Learning and Cybernetics.

[3]  Ali Pourmohammad,et al.  Using Single-Layer neural network for recognition of isolated handwritten Persian digits , 2009, 2009 7th International Conference on Information, Communications and Signal Processing (ICICS).

[4]  Ching Y. Suen,et al.  The State of the Art in Online Handwriting Recognition , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Yoshua Bengio,et al.  Gradient-based learning applied to document recognition , 1998, Proc. IEEE.

[6]  Sanjay S. Gharde,et al.  Support Vector Machine for Handwritten Devanagari Numeral Recognition , 2010 .

[7]  Thomas Martinetz,et al.  'Neural-gas' network for vector quantization and its application to time-series prediction , 1993, IEEE Trans. Neural Networks.

[8]  Robert H. Davis,et al.  Recognition of handwritten characters - a review , 1986, Image Vis. Comput..

[9]  Vladimir Vapnik,et al.  Statistical learning theory , 1998 .

[10]  Øivind Due Trier,et al.  Evaluation of Binarization Methods for Document Images , 1995, IEEE Trans. Pattern Anal. Mach. Intell..

[11]  L. D. Harmon,et al.  Automatic recognition of print and script , 1972 .

[12]  Teuvo Kohonen,et al.  Self-Organizing Maps , 2010 .

[13]  Faruq A. Al-Omari,et al.  Handwritten Indian numerals recognition system using probabilistic neural networks , 2004, Adv. Eng. Informatics.

[14]  Ching,et al.  The State of the Art in On-Line Handwriting Recognition , 2000 .

[15]  Apurva A. Desai,et al.  Gujarati handwritten numeral optical character reorganization through neural network , 2010, Pattern Recognit..

[16]  El-Sayed M. El-Alfy.  Offline Recognition of Handwritten Numeral Characters with Polynomial Neural Networks Using Topological Features , 2010, Canadian Conference on AI.

[17]  Masaki Nakagawa,et al.  'Online recognition of Chinese characters: the state-of-the-art , 2004, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Heekuck Oh,et al.  Neural Networks for Pattern Recognition , 1993, Adv. Comput..

[19]  Dong Yongfeng,et al.  Handwritten Chinese Characters Recognition Based on PSO Neural Networks , 2009, 2009 Second International Conference on Intelligent Networks and Intelligent Systems.

[20]  Michael T. Manry,et al.  Comparisons of a neural network and a nearest-neighbor classifier via the numeric handprint recognition problem , 1995, IEEE Trans. Neural Networks.

[21]  Cheng-Lin Liu,et al.  Handwritten digit recognition: benchmarking of state-of-the-art techniques , 2003, Pattern Recognit..

[22]  Putra Sumari,et al.  Digital Recognition using Neural Network , 2009 .