Common nature of learning between BP and hopfield-type neural networks for convex quadratic minimization with simplified network models

2009 IEEE International Conference on Mechatronics and Automation, ICMA 2009

Volumn , Issue , 2009, Pages 2500-2505

  Zhang, Yunong ^a   Shi, Yanyan ^a   Cai, Binghuang ^a   Li, Zhan ^a   Yi, Chenfu ^a   Mai, Jianzhang ^a  

^a SUN YAT SEN UNIVERSITY   (China)

Author keywords

BP neural networks; Common nature of learning; Convex quadratic minimization; Hopfield networks

Indexed keywords

BACK-PROPAGATION NEURAL NETWORKS; BP NEURAL NETWORKS; DISCRETE-TIME; HOPFIELD NETWORKS; HOPFIELD TYPE NEURAL NETWORKS; NETWORK MODELS; PHYSICAL MEANINGS; QUADRATIC MINIMIZATION; QUADRATIC OBJECTIVE FUNCTIONS; SIMPLIFIED MODELS; TRAINING PATTERNS; TWO LAYERS;

BACKPROPAGATION; COMPUTER SIMULATION; HOPFIELD NEURAL NETWORKS; MECHATRONICS; TRAVELING SALESMAN PROBLEM;

NEURAL NETWORKS;

EID: 77449097019     PISSN: None     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/ICMA.2009.5246519     Document Type: Conference Paper

References (19)

1. K. Pelckmans , M. Espinoza, J. De Brabanter, J. A. K. Suykens, and B. De Moor, "Primal-dual monotone kernel regression," Neural Processing Letters, vol. 22, no. 2, pp. 171-182, September 2005.
2. J. J. Wong and S. Y. Cho, "Local experts organization model for natural scene images classification," Neural Processing Letters, vol. 26, no. 2, pp. 83-99, July 2007.
3. Y. Zhang, "Towards piecewise-linear primal neural networks for optimization and redundant robotics," in Proceedings of IEEE International Conference on Networking, Sensing and Control, Florida, USA, pp. 374-379, August 2006.
4. I. Bonzani and R. Porro, "Optimization of traffic flow conditions by minimization of quadratic functionals," Mathematical and Computer Modelling, vol. 35, no. 5, pp. 673-681, March 2002.
5. J. S. Tsai, J. S. Li, and L. Shieh, "Discretized quadratic optimal control for continuous-time two-dimensional systems," IEEE Transactions on Circuits and Systems, Part I: Fundamental Theory and Applications, vol. 49, no. 1, pp. 116-125, January 2002.
6. H. W. Zhang, W. X. Zhong, C. H. Wu, and A. H. Liao, "Some advances and applications in quadratic programming method for numerical modeling of elastoplastic contact problems," International Journal of Mechanical Sciences, vol. 48, no. 2, pp. 176-189, February 2006.
7. Y. Zhang and J. Wang, "A dual neural network for convex quadratic programming subject to linear equality and inequality constraints," Physics Letters A, vol. 298, no. 4, pp. 271-278, June 2002.
8. Y. Zhang, S. S. Ge, and T. H. Lee, "A unified quadratic programming based dynamical system approach to joint torque optimization of physically constrained redundant manipulators," IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics, vol. 34, no. 5, pp. 2126-2132, October 2004.
9. S. Hong and S. Verma, "A note on the strong polynomiality of convex quadratic programming," Mathematical Programming, vol. 68, no. 1-3, pp. 131-139, May 1995.
10. Q. Tao, J. Cao, and D. Sun, "A simple and high performance neural network for quadratic programming problems," Applied Mathematics and Computation, vol. 124, no. 2, pp. 251-260, October 2001.
11. Y. Zhang, J. Mai, X. Xiao, Z. Li, and C. Yi, "The common nature of learning of the BP and Hopfield-type neural networks in the minimization of quadratic functions," Techniques of Automation and Applications, vol. 127, no. 9, pp. 5-10, September 2008.
12. Y. Zhang, Z. Li, K. Chen, and B. Cai, "Common nature of learning exemplified by BP and Hopfield neural networks for solving online a system of linear equations," in Proceedings of IEEE International Conference on Networking, Sensing and Control, Sanya, China, pp. 832-836, April 2008.
13. Z. Li, H. Zhang, W. Ma, and Y. Zhang, "Common nature of learning of BP and Hopfield neural networks exemplified via online solution of over-determined linear equations," in Teaching and Learning: Research and Practice, vol. II (Y. Zhong, Ed.), Guangzhou: Sun Yat-Sen University Press, 2007, pp. 875-886.
14. Z. Zeng, D. S. Huang, and Z. Wang, "Global convergence of steepest descent for quadrat ic functions," in Proceedings of the 5th International Conference of Intelligent Data Engineering and Automated Learning, Exeter, UK, vol. 3177, pp. 672-677, August 2004.
15. Z. Zeng, "Analysis of global convergence and learning parameters of the back-propagation algorithm for quadratic functions," in Proceedings of the 3rd International Conference on Intelligent Computing, Qingdao, China, vol. 4682 , pp. 7-13, July 2007.
16. D. W. Tank and J. J. Hopfield, "Simple 'neural' optimization networks: an A/D converter, signal decision network, and a linear programming circuit," IEEE Transactions on Circuits and Systems, vol. 33, no. 5, pp. 533-541, May 1986.
17. B. Llanas, S. Lantarón , and F. J. Sáinz, "Constructive approximation of discontinuous functions by neural networks," Neural Processing Letters, vol. 27, no. 3, pp. 209-226, June 2008.
18. Y. Zhang, X. Xu, and Z. Mao, "Java programming language with application in ANN," Journal of Jinan University, vol. 19, pp. 108-112, February 1998.
19. H. Demuth and M. Beale, MATLAB Neural Network Toolbox User's Guide, Version 4, The Mathworks Inc., Natick, MA, 2004.