Feedforward neural network training using intelligent global harmony search

被引:8
作者
Tavakoli, Saeed [1 ]
Valian, Ehsan [1 ]
Mohanna, Shahram [1 ]
机构
[1] Faculty of Electrical and Computer Engineering, University of Sistan and Baluchestan, Zahedan
关键词
Artificial neural network; Classification; Harmony search; Optimization;
D O I
10.1007/s12530-012-9054-5
中图分类号
学科分类号
摘要
Harmony search algorithm is a meta-heuristic optimization method imitating the music improvisation process, where musicians improvise their instruments' pitches searching for a perfect state of harmony. First, an improved harmony search algorithm is presented using the concept of swarm intelligence. Next, it is employed for training feedforward neural networks for three benchmark classification problems. Then, the performance of the proposed algorithm is compared with that of three methods. Simulation results demonstrate the effectiveness of the proposed algorithm. © 2012 Springer-Verlag.
引用
收藏
页码:125 / 131
页数:6
相关论文
共 37 条
[1]  
Ceylan H., Haidenbilen S., Et al., Transport energy modelling with meta-heuristic harmony search algorithm, an application to Turkey, Energy Policy, 36, 7, pp. 2527-2535, (2008)
[2]  
Chronopoulos A.T., Sarangapani J., A distributed discrete time neural network architecture for pattern allocation and control, Proceedings of the international parallel and distributed processing symposium, pp. 204-211, (2002)
[3]  
Curry B., Morgan P., Neural networks: a need for caution, OMEGA, Int J Manag Sci, 25, pp. 123-133, (1997)
[4]  
Degertekin S.O., Harmony search algorithm for optimum design of steel frame structures: a comparative study with other optimization methods, Struct Eng Mech, 29, 4, pp. 391-410, (2008)
[5]  
Degertekin S.O., Optimum design of steel frames using harmony search algorithm, Struct Multidiscip Optim, 36, 4, pp. 393-401, (2008)
[6]  
Fausett L., Fundamentals of Neural Networks Architectures, Algorithms, and Applications, (1994)
[7]  
Fesanghary M., Mahdavi M., Minary-Jolandan M., Alizadeh Y., Hybridizing harmony search algorithm with sequential quadratic programming for engineering optimization problems, Comput Method Appl Mech Eng, 197, 33-40, pp. 3080-3091, (2008)
[8]  
Forsati R., Haghighat A.T., Mahdavi M., Harmony search based algorithms for bandwidth-delay-constrained least-cost multicast routing, Comput Commun, 31, 10, pp. 2505-2519, (2008)
[9]  
Garro B.A., Sossa H., Vazquez R.A., Design of artificial neural networks using a modified particle swarm optimization algorithm, International joint conference on neural networks, pp. 938-945, (2009)
[10]  
Garro B.A., Sossa H., Vazquez R.A., Design of artificial neural networks using differential evolution algorithm, Proceedings of the 17th international conference on neural information processing: Models and applications, Part II, pp. 201-208, (2010)