Evolutionary optimization-based training of convolutional neural networks for OCR applications

2013 17th International Conference on System Theory, Control and Computing, ICSTCC 2013; Joint Conference of SINTES 2013, SACCS 2013, SIMSIS 2013 - Proceedings

Volumn , Issue , 2013, Pages 207-212

  Fedorovici, Lucian Ovidiu ^a   Precup, Radu Emil ^a   Dragan, Florin ^a   Purcaru, Constantin ^a  

^a POLITEHNICA UNIVERSITY OF TIMISOARA   (Romania)

Author keywords

back propagation; convolutional neural netrorks; Gravitational Search Algorithms; Particle Swarm Optimization

Indexed keywords

COMPUTATIONAL COSTS; CONVOLUTIONAL NEURAL NETRORKS; CONVOLUTIONAL NEURAL NETWORK; EVOLUTIONARY OPTIMIZATION ALGORITHM; GRAVITATIONAL SEARCH ALGORITHM (GSA); GRAVITATIONAL SEARCH ALGORITHMS; OPTICAL CHARACTER RECOGNITION (OCR); TRAINING ALGORITHMS;

LEARNING ALGORITHMS; NEURAL NETWORKS; OPTICAL CHARACTER RECOGNITION; PARTICLE SWARM OPTIMIZATION (PSO); SYSTEM THEORY;

BACKPROPAGATION ALGORITHMS;

EID: 84893223102     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICSTCC.2013.6688961     Document Type: Conference Paper

References (33)

1. V. Jain and H. S. Seung, "Natural image denoising with convolutional networks. Advances in neural information processing systems," in Proc. 22nd Annu. Conf. Neural Inf. Process. Syst. (NIPS 2008), Vancouver, BC, Canada, 2008, pp. 769-776.
2. S. C. Turaga, J. F. Murray, V. Jain, F. Roth, M. Helmstaedter, K. Briggman, W. Denk, and H. S. Seung, "Convolutional networks can learn to generate affinity graphs for image segmentation," Neural Comput., vol. 22, pp. 511-538, Feb. 2010.
3. D. C. Ciresan, U. Meier, L. M. Gambardella, and J. Schmidhuber, "Convolutional neural network committees for handwritten character classification," in Proc. 11th Int. Conf. Document Analysis and Recognition, Manno-Lugano, Switzerland, 2011, pp. 1135-1139.
4. K. Kavukcuoglu, P. Sermanet, Y. Boureau, K. Gregor, M. Mathieu, and Y. LeCun, "Learning convolutional feature hierarchies for visual recognition," in Proc. 24th Annu. Conf. Neural Inf. Process. Syst. (NIPS 2010), Vancouver, BC, Canada, 2010, pp. 1090-1098.
5. P. Y. Simard, D. Steinkraus, and J. Platt, "Best practices for convolutional neural networks applied to visual document analysis," in Proc. 7th Int. Conf. Document Analysis and Recognition (ICDAR 2003), Edinburgh, UK, 2003, pp. 958-962.
6. L. Bottou, Y. LeCun, and Y. Bengio, "Global training of document processing systems using graph transformer networks," in Proc. IEEE Comput. Soc. Conf. Comput. Vision Pattern Recognit., San Juan, Puerto Rico, 1997, pp. 489-494.
7. Y. LeCun, B. Boser, J. S. Denker, D. Henderson, R. E. Howard, W. Hubbard, and L. D. Jackel, "Handwritten digit recognition with a backpropagation network," in Advances in Neural Information Processing Systems. San Francisco, CA: Morgan Kaufmann, 1990, vol. 2, pp. 396-404.
8. Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner, "Gradient-based learning applied to document recognition," Proc. IEEE, vol. 86, pp. 2278-2324, Nov. 1998.
9. F. H. C. Tivive and A. Bouzerdoum, "Efficient training algorithms for a class of shunting inhibitory convolutional neural networks," IEEE Trans. Neural Netw., vol. 16, pp. 541-556, May 2005.
10. S. Haykin, Neural Networks. A Comprehensive Foundation, 2nd ed. Englewood Cliffs, NJ: Prentice-Hall, 1998.
11. J. Kennedy and R. C. Eberhart, "Particle swarm optimization," in Proc. IEEE Int. Conf. Neural Netw. (ICNN'95), Perth, WA, Australia, 1995, vol. 4, pp. 1942-1948.
12. E. Rashedi, H. Nezamabadi-pour, and S. Saryazdi, "GSA: A gravitational search algorithm," Inf. Sci., vol. 179, pp. 2232-2248, Jun. 2009.
13. L.-O. Fedorovici, R.-E. Precup, F. Dragan, R.-C. David, and C. Purcaru, "Embedding gravitational search algorithms in convolutional neural networks for OCR applications," in Proc. IEEE 7th Int. Symp. Appl. Comput. Intell. Informat. (SACI 2012), Timisoara, Romania, 2012, pp. 125-130.
14. W. Zhang, P. Niu, G. Li, and P. Li, "Forecasting of turbine heat rate with online least squares support vector machine based on gravitational search algorithm," Knowl.-Based Syst., vol. 39, pp. 34-44, Feb. 2013.
15. R. Eberhart, "A new optimizer using particle swarm theory," in Proc. 6th Int. Conf. Micro Machine and Human Sci. (MHS '95), Nagoya, Japan, 1995, pp. 39-43.
16. G. Zhitao, "Handwritten Chinese characters recognition based on PSO neural networks," in Proc. 2nd Int. Conf. Intell. Netw. Intell. Syst. (ICINIS '09), Tianjin, China, 2009, pp. 350-353.
17. L. Cheng-Jian and L. Chi-Yung, "Non-linear system control using a recurrent fuzzy neural network based on improved particle swarm optimization," Int. J. Syst. Sci., vol. 41, pp. 381-395, Apr. 2010.
18. W. Li, Q. Yao, and C. Deng, "Application of the BP neural network based on PSO in dynamic gesture recognition," Comp. Eng. Sci., vol. 33, pp. 74-79, May 2011.
19. B. Luitel and G. K. Venayagamoorthy, "Quantum inspired PSO for the optimization of simultaneous recurrent neural networks as MIMO learning systems," Neural Netw., vol. 23, pp. 583-586, Jun. 2010.
20. B. A. Garro, H. Sossa, and R. Vazquez, "Back-propagation vs. particle swarm optimization algorithm: which algorithm is better to adjust synaptic weights of a feed-forward ANN?," Int. J. Artif. Intell., vol. A11, pp. 208-218, Oct. 2011.
21. M. Yaghini, M. M. Khoshraftar, and M. Fallahi, "A hybrid algorithm for artificial neural network training," Eng. Appl. Artif. Iintell., vol. 26, pp. 293-301, Jan. 2013.
22. Z. Liu, H. Cao, X. Chen, Z. He, and Z. Shen, "Multi-fault classification based on wavelet SVM with PSO algorithm to analyze vibration signals from rolling element bearings," Neurocomput., vol. 99, pp. 399-410, Jan. 2013.
23. S. C. Chiam, K. C. Tan, and A. A. Mamun, "A memetic model of evolutionary PSO for computational finance applications," Expert Syst. Appl., vol. 36, pp. 3695-3711, Mar. 2009.
24. E. Zahara and Y.-T. Kao, "Hybrid Nelder-Mead simplex search and particle swarm optimization for constrained engineering design problems," Expert Syst. Appl., vol. 36, pp. 3880-3886, Mar. 2009.
25. R.-E. Precup, R.-C. David, E. M. Petriu, M.-B. Radac, S. Preitl, and J. Fodor, "Evolutionary optimization-based tuning of low-cost fuzzy controllers for servo systems," Knowl.-Based Syst., vol. 38, pp. 74-84, Jan. 2013.
26. P. Baranyi, D. Tikk, Y. Yam, and R. J. Patton, "From differential equations to PDC controller design via numerical transformation," Comp. Ind., vol. 51, pp. 281-297, Aug. 2003.
27. I. Škrjanc, S. BlaziC, S. Oblak, and J. Richalet, "An approach to predictive control of multivariable time-delayed plant: Stability and design issues," ISA Trans., vol. 43, pp. 585-595, Oct. 2004.
28. H.-N. Teodorescu, "Parallelizing dynamic models based on fuzzy coupled map networks," in Proc. 4th IEEE Workshop Intell. Data Acquisition Adv. Comput. Syst. Tech. Appl. (IDAACS 2007), Dortmund, Germany, 2007, pp. 170-175.
29. J. VaŜCák and M. Rutrich, "Path planning in dynamic environment using fuzzy cognitive maps," in Proc. 6th Int. Symp. Appl. Machine Intell. Informat. (SAMI 2008), Herlany, Slovakia, 2008, pp. 5-9.
30. B. Dankovic, S. Nikolic, M. Milojkovic, and Z. Jovanovic, "A class of almost orthogonal filters," J. Circ. Syst. Comput., vol. 18, no. 5, pp. 923-931, Aug. 2009.
31. D. Tikk, Z. C. Johanyák, S. Kovács, and K. W. Wong, "Fuzzy rule interpolation and extrapolation techniques: Criteria and evaluation guidelines," J. Adv. Comp. Intell. Intell. Informat., vol. 15, pp. 254-263, May 2011.
32. E. S. Nicoara, F.-G. Filip, and N. Paraschiv, "Simulation-based optimization using genetic algorithms for multi-objective flexible JSSP," Stud. Informat. Control, vol. 20, pp. 333-344, Dec. 2011.
33. N. Bouhmala, "A multilevel memetic algorithm for the satisfiability problem," Int. J. Artif. Intell., vol. 8, pp. 78-96, Mar. 2012.