Logo PTI
Polish Information Processing Society
Logo FedCSIS

Annals of Computer Science and Information Systems, Volume 11

Proceedings of the 2017 Federated Conference on Computer Science and Information Systems

The Realisation of Neural Network Structural Optimization Algorithm

, ,

DOI: http://dx.doi.org/10.15439/2017F448

Citation: Proceedings of the 2017 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 11, pages 1365–1371 ()

Full text

Abstract. This paper presents a deep analysis of literature on the problems of optimization of parameters and structure of the neural networks and the basic disadvantages that are present in the observed algorithms and methods. As a result, there is suggested a new algorithm for neural network structure optimization, which is free of the major shortcomings of other algorithms. The paper describes a detailed description of the algorithm, its implementation and application for recognition problems.

References

  1. Q. Xiao, W. Shi, X. Xian and X. Yan, “An image restoration method based on genetic algorithm BP neural network”, Proceedings of the 7th World Congress on Intelligent Control and Automation, pp. 7653-7656, 2008.
  2. W. Wu, W. Guozhi, Z. Yuanmin and W. Hongling, “Genetic Algorithm Optimizing Neural Network for Short-Term Load Forecasting”, International Forum on Information Technology and
  5. Applications, pp. 583-585, 2009. S. Zeng, J. Li and L. Cui, “Cell Status Diagnosis for the Aluminum Production on BP Neural Network with Genetic Algorithm”, Communications in Computer and Information Science, Vol. 175, pp. 146-152, 2011. W. Yinghua and X. Chang, “Using Genetic Artificial Neural Network to Model Dam Monitoring Data”, Second International Conference on Computer Modeling and Simulation, pp. 3-7, 2010. R. Sulej, K. Zaremba, K. Kurek and R. Rondio, “Application of the Neural Networks in Events Classification in the Measurement of the Spin Structure of the Deuteron”, Warsaw University of Technology, Poland, 2007.
  6. S. A. Harp and T. Samad, “Genetic Synthesis of Neural Network Architecture”, Handbook of Genetic Algorithms, pp. 202-221, 1991.
  7. D. Whitley, T. Starkweather and C. Bogart, “Genetic Algorithms and Neural Networks: Optimizing Connections and Connectivity”, Parallel Computing, Vol. 14, pp. 347-361, 1990.
  8. V. Bevilacqua, G. Mastronardi, F. Menolascina, P. Pannarale and A. Pedone, “A Novel Multi-Objective Genetic Algorithm Approach to Artificial Neural Network Topology Optimisation: The Breast Cancer Classification Problem”, International Joint Conference on Neural Networks, pp. 1958-1965, 2006.
  9. Y. Du and Y. Li, “Sonar array azimuth control system based on genetic neural network”, Proceedings of the 7th World Congress on Intelligent Control and Automation, pp. 6123-6127, 2008.
  10. S. Nie and B. Ye, “The Application of BP Neural Network Model of DNA-Based Genetic Algorithm to Monitor Cutting Tool Wear”, International Conference on Measuring Technology and Mechatronics Automation, pp. 338-341, 2009.
  11. C. Tang, Y. He and L. Yuan, “A Fault Diagnosis Method of Switch Current Based on Genetic Algorithm to Optimize the BP Neural Network”. International Conference on Electric and Electronics, Vol. 99, pp. 943-950, 2011.
  12. Y. Du and Y. Li, “Sonar array azimuth control system based on genetic neural network”, Proceedings of the 7th World Congress on Intelligent Control and Automation, pp. 6123-6127, 2008.
  13. L. Jinru, L. Yibing and Y. Keguo, “Fault diagnosis of piston compressor based on Wavelet Neural Network and Genetic Algorithm”. Proceedings of the 7th World Congress on Intelligent Control and Automation, pp. 6006-6010, 2008.
  14. D. Dasgupta and D. R. McGregor, “Designing Application-Specific Neural Networks using the Structured Genetic Algorithm”, Proceedings of International Workshop on Combinations of Genetic Algorithms and Neural Networks, pp. 87-96, 1992.
  15. G. G. Yen and H. Lu, “Hierarchical Genetic Algorithm Based Neural Network Design”, IEEE Symposium on Combinations of Evolutionary Computation and Neural Networks, pp. 168-175, 2000.
  16. P. Koehn, “Combining Genetic Algorithms and Neural Networks: The Encoding Problem”, University of Tennessee, Knoxville, 1994.
  17. Z. Chen, “Optimization of Neural Network Based on Improved Genetic Algorithm”, International Conference on Computational Intelligence and Software Engineering, pp.1-3, 2009.
  18. P. W. Munro, “Genetic Search for Optimal Representation in Neural Networks”, Proceedings of the International Joint Conference on Neural Networks and Genetic Algorithms, pp. 675-682, 1993.
  19. X. Fu, P.E.R. Dale and S. Zhang, “Evolving Neural Network Using Variable String Genetic Algorithms (VGA) for Color Infrared Aerial Image Classification”, Chinese Geographical Science, Vol. 18(2), pp. 162-170, 2008.
  20. J. M. Bishop and M. J. Bushnell, “Genetic Optimization of Neural Network Architectures for Colour Recipe Prediction”, Proceedings of the International Joint Conference on Neural Networks and Genetic Algorithms, pp. 719-725, 1993.
  21. M. Mezard, J.P. Nadal, “Learning in feedforward layered networks: The Tiling algorithm”, Journal of Physics, 1989, V. A22, P. 2191 – 2203.
  22. M. Frean, “The Upstart Algorithm: A Method for Constructing and Training Feed-Forward Neural Networks”, Tech. Rep. 89/469, Edinburgh University, 1989.
  23. B. D. Ripley, “Pattern recognition and neural networks”, Cambridge: Cambridge Univ. Press, 2009.
  24. Y.Y. Dorogiy, “Accelerated learning algorithm of Convolutional neural networks”, Y.Y. Dorogiy, Visnik NTUU «KPI», «Informatika, upravlinnya ta obchislyuvalna tehnika», #57, 2012, S. 150-154.
  25. Ya. Yu. Dorohyy, “The algorithm of algorithmic optimization of the structural neural network is based on classification of data”, / Ya. Yu. Dorohyy, V. V. Tsurkan, O. O. Doroha-Ivanyuk, D. A. Ferens, Visnyk NTUU «KPI», «Informatyka, upravlinnya ta obchyslyuval'na tekhnika», #62, 2015, S. 169-173.
  26. S. D. Halloway, “Programming Clojure”, Dalles, Tex.[u.a.] : The Pragmatic Bookshelf, 2012. 2nd ed.
  27. B. Goetz, “Java Concurrency in Practice”, Addison-Wesley Professional; 1 edition, 2006.
  28. Yale Face Database. homepage: http://vision.ucsd.edu/~iskwak/ExtYaleDatabase/Yale/Face/Database.htm (online).
  29. Yoshua Bengio, “Practical recommendations for gradient-based training of deep architectures”, https://arxiv.org/abs/1206.5533v2, 2012.
  30. Hüsken, M., Jin, Y. & Sendhoff, B. Soft Computing (2005) 9: 21. http://dx.doi.org/10.1007/s00500-003-0330-y.
  31. Peter Sadowski, "Notes on backpropagation", homepage: https://www.ics. uci.edu/~pjsadows/notes.pdf (online).