Optimization of a modular neural network for pattern recognition using parallel genetic algorithm

• Autorzy: Cárdenas M. , Melin P. , Cruz L.
• Konferencja: International Seminar on Computational Intelligence, January 2010, Tijuana, Mexico
• Języki publikacji: EN

Abstrakty

EN

In this paper, the implementation of a Parallel Genetic Algorithm (PGA) for the training stage, and the optimi zation of a monolithic and modular neural network, for pattern recognition are presented. The optimization con sists in obtaining the best architecture in layers, and neu rons per layer achieving the less training error in a shor ter time. The implementation was performed in a multicore architecture, using parallel programming techniques to exploit its resources. We present the results obtained in terms of performance by comparing results of the training stage for sequential and parallel implementations.

Słowa kluczowe

EN

modular neural networks; parallel genetic algorithm; multi-core

• Wydawca: Łukasiewicz Industrial Research Institute for Automation and Measurements PIAP
• Czasopismo: Journal of Automation Mobile Robotics and Intelligent Systems
• Rocznik: 2011
• Tom: Vol. 5, No. 1
• Strony: 77--84
• Opis fizyczny: Bibliogr. 26 poz., rys.

Twórcy

autor

Cárdenas M.

autor

Melin P.

autor

Cruz L.

• Tijuana Institute of Technology, Tijuana, México,

Bibliografia

• [1] E.Alba,A.Nebro,J.Troya,“HeterogeneousComputing and Parallel Genetic Algorithms”, Journal of Parallel and Distributed Computing , vol. 62, 2002, pp. 13621385.
• [2] C. Baldwin, K. Clark, Design Rules, Vol. 1: The Power of Modularity , Mit Press, Cambridge, 2000.
• [3] T.W. Burger, Intel Multi-Core Processors: Quick Reference Guide, http://cachewww.intel.com/cd/00/00/20/ 57/205707_205707.pdf
• [4] E. Cantu-Paz, Efficient and Accurate Parallel Genetic Algorithms, KluwerAcademic Publisher, 2001.
• [5] M. Cárdenas, J. Tapia, O. Montiel, R. Sepúlveda, “Neurofuzzy system implementation in Multicore Processors”, IV Regional Academic Encounter , CITEDIIPN, 2008.
• [6] O. Castillo, P. Melin, “Hybrid intelligent systems for time series prediction using neural networks, fuzzy logic and fractal theory”, IEEE Transactions on Neural Networks, vol. 13, no. 6, 2002.
• [7] L. Chai, Q. Gao, D.K. Panda, “Understanding the Impact of Multi-Core Architecture in Cluster Computing: A Case Study with Intel Dual-Core System”. In: The 7 th IEEE International Symposium on Cluster Computing and the Grid (CCGrid 2007). May 2007, pp. 471-478.
• [8] C.A. Coello, G.B. Lamont, D.A. Van Veldhuizen, Evolutionary Algorithms for Solvin Multi-Objective Problem , Springer: Heidelberg, 2004.
• [9] The Database of Faces, Cambridge University Computer Laboratory, http://www.cl.cam.ac.uk/research/ dtg/attarchive/facedatabase.html
• [10] J. Dongarra, I. Foster, G. Fox, W. Gropp, K. Kennedy, L. Torczon, A. White, Sourcebook of Parallel Computing, Morgan Kaufmann PublishersL San Francisco, 2003.
• [11] S. González, Optimization of Artificial Neural Network Architectures for time series prediction using Parallel Genetic Algorithms . Master thesis, 2007.
• [12] K. Hornik, “Some new results on neural network approximation,'' Neural Networks , vol. 6, 1993, pp. 10691072.
• [13] A. Jeffrey, V. Oklobdzija, The computer Engineering Handbook, Digital Systems and Aplications , 2 nd edition, CRC press, 1993.
• [14] P. Kouchakpour, A. Zaknich, T. Bräunl, Population Variation in Genetic Programming , Elsevier Science Inc, ISSN:0020-0255, 2007.
• [15] P. Melin, O. Castillo , Hybrid Intelligent Systems for Pattern Recognition using Soft Computing: An Evolutionary Approach for Neural Networks and Fuzzy Systems , Springer, 2005.
• [16] P. Melin, O. Castillo, Hybrid Intelligent Systems for Pattern Recognition Using Soft Computing . Springer, Heidelberg, 2005.
• [17] B. Morcego, Study of modular neural networks for modeling nonlinear dynamic systems , PhD thesis, Universitat Politecnica de Catalunya, Barcelona, Spain, 2000.
• [18] I. Quiliano, Sistemas Modulares, Mezcla de Expertos y Sistemas Híbridos, February 2007, in Spanish, http://lisisu02.usal.es/~airene/capit7.pdf
• [19] M. Mitchell, An introduction to genetic algorithms , MIT Press, 1998.
• [20] M. Nowostawski, R. Poli, “Parallel Genetic Taxonomy”, In: Proceedings of the Third International Conference in Knowledge-Based Intelligent Information Engineering Systems, December 1999, pp. 88-92. DOI: 10.1109/KES.1999.820127.
• [21] A. Ross, K. Nandakumar, A.K. Jainet, Handbook of Multibiometrics, Springer 2006.
• [22] P. Salazar, "Biometric recognition using techniques of hand geometry and voice with computer vision for feature extraction, neural networks and fuzzy logic ", Master thesis, Division of Graduate Studies and Research in Computer Science , ITT, 2008, p. 57.
• [23] R. Salinas, Neural Network Architecture Parametric Face Recognition , University of Santiago of Chile, 2000, pp. 5-9. http://cabierta.uchile.cl/revista/17/artículos/paper4/index.html
• [24] R. Serrano, Multicore computing applied to Genetic Algorithms. Master. Thesis, CITEDI-IPN, 2008.
• [25] M. Shorlemmer, “Basic Tutorial of Neural Networks”. In: Artificial Intelligence Research Institute , Barcelona, Spain, 1995.
• [26] M. Soto Castro, Face and Voice Recognition in real time using Artificial Neural Networks , Master Thesis, Tijuana Institute of Technology, 2006.