A new learning algorithm with logarithmic performance index for complex-valued neural networks

Neurocomputing

Volumn 72, Issue 16-18, 2009, Pages 3771-3781

  Savitha, R ^a   Suresh, S ^b   Sundararajan, N ^a   Saratchandran, P ^a  

^a NANYANG TECHNOLOGICAL UNIVERSITY   (Singapore)

^b Korea University   (South Korea)

Author keywords

Fully complex valued networks; Logarithmic performance index; Multi layer perceptron; Split complex network

Indexed keywords

ACTIVATION FUNCTIONS; COMPARATIVE ANALYSIS; COMPLEX VALUED FUNCTIONS; COMPLEX-VALUED NEURAL NETWORKS; CONVERGENCE CHARACTERISTICS; EQUALIZATION PROBLEM; FEED-FORWARD NETWORK; FULLY COMPLEX-VALUED NETWORKS; FUNCTION APPROXIMATION PROBLEMS; INITIAL WEIGHTS; LEARNING RATES; LEARNING SAMPLES; LOGARITHMIC PERFORMANCE INDEX; MULTI-LAYER PERCEPTRON; NON-MINIMUM PHASE; PERFORMANCE INDICES; PHASE ERROR; SENSITIVITY STUDIES; SOURCE LOCALIZATION; SPLIT COMPLEX NETWORK;

ACTIVATION ANALYSIS; APPROXIMATION ALGORITHMS; BACKPROPAGATION ALGORITHMS; CHLORINATION; CONTEXT SENSITIVE GRAMMARS; CONVERGENCE OF NUMERICAL METHODS; EDUCATION; LEARNING SYSTEMS; MEDICAL IMAGING; MEDICAL PROBLEMS; NEURAL NETWORKS; SENSITIVITY ANALYSIS;

LEARNING ALGORITHMS;

ANALYTICAL ERROR; ARTICLE; ARTIFICIAL NEURAL NETWORK; BACK PROPAGATION; CONTROLLED STUDY; DIAGNOSTIC IMAGING; LEARNING ALGORITHM; PERCEPTRON; PRIORITY JOURNAL; SENSITIVITY ANALYSIS; TELECOMMUNICATION;

EID: 69249205575     PISSN: 09252312     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.neucom.2009.06.004     Document Type: Article

References (18)

1. Kim T., and Adali T. Fully-complex multilayer perceptron network for nonlinear signal processing. Journal of VLSI Signal Processing 32 1-2 (2002) 29-43
2. Leung H., and Haykin S. Complex backpropagation algorithm. IEEE Transactions on Signal Processing 39 9 (1991) 2101-2104
3. Jianping D., Sundararajan N., and Saratchandran P. Complex-valued minimal resource allocation network for nonlinear signal processing. International Journal of Neural Systems 10 2 (2000) 95-106
4. N. Benvenuto, M. Marchesi, F. Piazza, A. Uncini, A comparison between real and complex-valued neural networks in communication applications, in: Proceedings of the International Neural Networks Conference, Helsinki, Finland, June 1991, pp. 1177-1180.
5. N. Benvenuto, M. Marchesi, F. Piazza, A. Uncini, Nonlinear satellite radio links equalized using blind neural networks, in: Proceedings of the International Conference ASSP, Toronto, Canada, April 1991, pp. 1521-1524.
6. Yang S.S., Ho C.L., and Siu S. Sensitivity analysis of the split-complex valued multilayer perceptron due to the errors of the i.i.d. inputs and weights. IEEE Transactions on Neural Networks 18 5 (2007) 1280-1293
7. Loss D.V., DeCastro M.C.F., Franco P.R.G., and DeCastro F.C.C. Phase transmittance RBF neural networks. Electronics Letters 43 16 (2007) 882-884
8. Georgios G.M., and Koutsougeras C. Complex domain backpropagation. IEEE Transactions on Circuit and Systems II 39 5 (1992) 330-333
9. You C., and Hong D. Nonlinear blind equalization schemes using complex valued multilayer feedforward neural networks. IEEE Transactions on Neural Networks 9 6 (1998) 1442-1455
10. Goh S.L., and Mandic D.P. An augmented extended Kalman filter algorithm for complex-valued recurrent neural networks. Neural Computation 19 4 (2007) 1039-1055
11. Benvenuto N., and Piazza F. On the complex backpropagation algorithm. IEEE Transactions on Signal Processing 40 4 (1992) 967-969
12. Deng J.P., Sundararajan N., and Saratchandran P. Communication channel equalization using complex-valued minimal radial basis function neural networks. IEEE Transactions on Neural Networks 13 3 (2002) 687-696
13. Kim T., and Adali T. Approximation by fully complex multilayer perceptrons. Neural Computation 15 7 (2003) 1641-1666
14. Suresh S., Omkar S.N., Mani V., and Guru Prakash T.N. Lift coefficient prediction at high angle of attack using recurrent neural network. Aerospace Science and Technology 7 8 (2003) 595-602
15. P.K.K. Anita, S. Gangal, D.S. Chauhan, Performance evaluation of complex-valued neural networks using various error functions, in: Proceedings of the World Academy of Science Engineering and Technology, vol. 23, August 2007, pp. 27-32.
16. Nitta T. An extension of the back-propagation algorithm to complex numbers. Neural Networks 10 8 (1997) 1391-1415
17. Cha I., and Kassam S.A. Channel equalization using adaptive complex radial basis function networks. IEEE Journal on Selected Areas in Communications 13 1 (1995) 122-131
18. Li M.-B., Huang G.-B., Saratchandran P., and Sundararajan N. Fully complex extreme learning machines. Neurocomputing 68 (2005) 306-314