Abstract
We describe in this paper the use of Modular Neural Networks (MNN) for pattern recognition with parallel processing using a cluster of computers with a master-slave topology. In this paper, we are proposing the use of MNN for face recognition with large databases to validate the efficiency of the proposed approach. Also, a parallel genetic algorithm for architecture optimization was used to achieve an optimal design of the MNN. The main idea of this paper is the use of parallel genetic algorithms to find the best architecture with large databases of faces, because when the database to be considered is large, the main problem is the processing time to train the MNN. Network parameters are adjusted by a combination of the training pattern set and the corresponding errors between the desired output and the actual network response. To control a learning process, a criterion is needed to decide the time for terminating the process.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Azam, F.: Biologically inspired modular neural networks. Ph.D. thesis, Citeseer (2000)
Azam, F., VanLandingham, H.: A modular neural network method for robust handwritten character recognition. In: Artificial Neural Networks for Intelligent Engineering, vol. 98, pp. 503–508 (1998)
Back, T., Fogel, D., Michalewicz, Z.: Handbook of Evolutionary Computation. Oxford University Press, Oxford (1997)
Baesens, B., et al.: Neural networks and learning systems come together. IEEE Trans. Neural Netw. Learn. Syst. 23(1), 1–6 (2012). https://doi.org/10.1109/TNNLS.2011.2180851
Castillo, O., Melin, P.: Hybrid intelligent systems for time series prediction using neural networks, fuzzy logic, and fractal theory. IEEE Trans. Neural Netw. 13(6), 1395–1408 (2002)
Gaxiola, F., Melin, P., Valdez, F., Castro, J.R.: Person recognition with modular deep neural network using the iris biometric measure. In: Castillo, O., Melin, P., Kacprzyk, J. (eds.) Fuzzy Logic Augmentation of Neural and Optimization Algorithms: Theoretical Aspects and Real Applications. SCI, vol. 749, pp. 69–80. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-71008-2_6
Gaxiola, F., Melin, P., Valdez, F., Castro, J.R., Manzo-Martinez, A.: PSO with dynamic adaptation of parameters for optimization in neural networks with interval type-2 fuzzy numbers weights. Axioms 8(1), 14 (2019). https://doi.org/10.3390/axioms8010014
Gaxiola, F., Melin, P., Valdez, F., Castro, J.R.: Optimization of deep neural network for recognition with human iris biometric measure. In: Melin, P., Castillo, O., Kacprzyk, J., Reformat, M., Melek, W. (eds.) NAFIPS 2017. AISC, vol. 648, pp. 172–180. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-67137-6_19
Goldberg, D.: Genetic Algorithms. Addison Wesley, Boston (1988)
Holland, J.: Adaptation in Natural and Artificial System. The University of Michigan Press, Ann Arbor (1975)
Lee, T.: Structure level adaptation for artificial neural networks. Springer, Boston (1991). https://doi.org/10.1007/978-1-4615-3954-4. Kluwer Academic Publishers
Ma, S., Ji, C.: Performance and efficiency: recent advances in supervised learning. Proc. IEEE 87(9), 1519–1535 (1999)
Man, K., Tang, S., Kwong, K.: Genetic Algorithms: Concepts and Designs. Springer, Heidelberg (1999). https://doi.org/10.1007/978-1-4471-0577-0
Muller, B., Reinhardt, J., Strickland, M.: Neural networks: An Introduction. Springer, Berlin (1995). https://doi.org/10.1007/978-3-642-57760-4
Neo, H., Teoh, B.: a novel spatially confined non-negative matrix factorization for face recognition. Science City, Japan, Tsukuba (2005)
Rumelhart, D.E., Hinton, G.E., Williams, R.J., et al.: Learning representations by back-propagating errors. Nature 323(6088), 533–536 (1986). https://doi.org/10.1038/323533a0
Seiffert, U.: Artificial neural networks on massively parallel computer hardware. In: ESANN, pp. 319–330 (2002)
Spacek, L.: Face Recognition Data, University of Essex, UK (2010). https://cswww.essex.ac.uk/mv/allfaces/
Mandal, T., Majumdar, A., Wu, Q.M.J.: Face recognition by curvelet based feature extraction. In: Kamel, M., Campilho, A. (eds.) ICIAR 2007. LNCS, vol. 4633, pp. 806–817. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-74260-9_72
Valdez, F., Melin, P., Castillo, O.: Evolutionary method combining particle swarm optimisation and genetic algorithms using fuzzy logic for parameter adaptation and aggregation: the case neural network optimization for face recognition. Int. J. Artif. Intell. Soft Comput. 2(1/2), 77–102 (2010)
Valdez, F., Vázquez, J., Gaxiola, F.: Fuzzy dynamic parameter adaptation in ACO and PSO for designing fuzzy controllers: the cases of water level and temperature control. Adv. Fuzzy Syst. 2018, 19 (2018). https://doi.org/10.1155/2018/1274969
Valdez, F., Castillo, O., Jain, A., Jana, D.K.: Nature-inspired optimization algorithms for neuro-fuzzy models in real-world control and robotics applications. Comput. Int. Neurosc. 2019, 2 (2019). https://doi.org/10.1155/2019/9128451
Acknowledgement
We would like to express our gratitude to CONACYT, Tijuana Institute of Technology for the facilities and resources granted for the development of this research, and Dr. Libor Spacek for the facilities of the face recognition database.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Valdez, F., Melin, P., Castillo, O. (2019). Optimization of Modular Neural Networks for Pattern Recognition with Parallel Genetic Algorithms. In: Martínez-Villaseñor, L., Batyrshin, I., Marín-Hernández, A. (eds) Advances in Soft Computing. MICAI 2019. Lecture Notes in Computer Science(), vol 11835. Springer, Cham. https://doi.org/10.1007/978-3-030-33749-0_19
Download citation
DOI: https://doi.org/10.1007/978-3-030-33749-0_19
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-33748-3
Online ISBN: 978-3-030-33749-0
eBook Packages: Computer ScienceComputer Science (R0)