Fully Complex MultiLayer Perceptron Network for Nonlinear Signal Processing
 Taehwan Kim,
 Tülay Adali
 … show all 2 hide
Rent the article at a discount
Rent now* Final gross prices may vary according to local VAT.
Get AccessAbstract
Designing a neural network (NN) to process complexvalued signals is a challenging task since a complex nonlinear activation function (AF) cannot be both analytic and bounded everywhere in the complex plane ℂ. To avoid this difficulty, ‘splitting’, i.e., using a pair of real sigmoidal functions for the real and imaginary components has been the traditional approach. However, this ‘ad hoc’ compromise to avoid the unbounded nature of nonlinear complex functions results in a nowhere analytic AF that performs the error backpropagation (BP) using the split derivatives of the real and imaginary components instead of relying on welldefined fully complex derivatives. In this paper, a fully complex multilayer perceptron (MLP) structure that yields a simplified complexvalued backpropagation (BP) algorithm is presented. The simplified BP verifies that the fully complex BP weight update formula is the complex conjugate form of real BP formula and the split complex BP is a special case of the fully complex BP. This generalization is possible by employing elementary transcendental functions (ETFs) that are almost everywhere (a.e.) bounded and analytic in ℂ. The properties of fully complex MLP are investigated and the advantage of ETFs over split complex AF is shown in numerical examples where nonlinear magnitude and phase distortions of nonconstant modulus modulated signals are successfully restored.
 Silverman, H. (1975) Complex Variables. Houghton, Newark, USA
 Clarke, T. (1990) Generalization of Neural Network to the Complex Plane. Proc. of IJCNN 2: pp. 435440
 Georgiou, G., Koutsougeras, C. (1992) Complex Backpropagation. IEEE Trans. on Circuits and Systems II 39: pp. 330334
 You, C., Hong, D. (1998) Nonlinear Blind Equalization Schemes Using ComplexValued Multilayer Feedforward Neural Networks. IEEE Trans. on Neural Networks 9: pp. 14421455
 D. Mandic and J. Chambers, Recurrent Neural Networks for Prediction, John Wiley and Sons, 2001.
 Hirose, A. (1992) Continuous ComplexValued BackPropagation Learning. Electronics Letters 28: pp. 18541855
 Leung, H., Haykin, S. (1991) The Complex Backpropagation Algorithm. IEEE Trans. on Signal Proc. 3: pp. 21012104
 Benvenuto, N., Marchesi, M., Piazza, F., Uncini, A. (1991) Non Linear Satellite Radio Links Equalized Using Blind Neural Networks. Proc. of ICASSP 3: pp. 15211524
 Benvenuto, N., Piazza, F. (1992) On the Complex Backpropagation Algorithm. IEEE Trans. on Signal Processing 40: pp. 967969
 Ibnkahla, M., Castanie, F. (1995) Vector Neural Networks for Digital Satellite Communications. Proc. of ICC 3: pp. 18651869
 A. Uncini, L. Vecci, P. Campolucci, and F. Piazza, “ComplexValued Neural Networks with Adaptive Spline Activation Functions,” IEEE Trans. on Signal Processing, vol. 47,no. 2, 1999.
 Bandito, S., Biglieri, E. (1983) Nonlinear Equalization of Digital Satellite Channels. IEEE Jour. on SAC. SAC1: pp. 5762
 Kechriotis, G., Manolakos, E. (1994) Training Fully Recurrent Neural Networks with Complex Weights. IEEE Trans. on Circuits and Systems—II: Analog and Digital Signal Processing 41: pp. 235238
 Deng, J., Sundararajan, N., Saratchandran, P. (2000) Communication Channel Equalization Using ComplexValued Minimal Radial Basis Functions Neural Network. Proc. of IEEE IJCNN 2000 5: pp. 372377
 Lee, K.Y., Jung, S. (1999) Extended Complex RBF and its Application to MQAM in Presence of CoChannel Interference. Electronics Letters 35: pp. 1719
 S. Chen, P.M. Grant, S. McLaughlin, and B. Mulgrew, “ComplexValued Radial Basis Function Networks,” in Proc. of third IEEE International Conference on Artificial Neural Networks,” 1993, pp. 148152.
 T. Kim and T. Adah, “Fully Complex Backpropagation for Constant Envelop Signal Processing,” in Proc. of IEEE Workshop on Neural Networks for Sig. Proc., Sydney, Dec. 2000, pp. 231240.
 T. Kim and T. Adah, “Complex Backpropagation Neural Network Using Elementary Transcendental Activation Functions,” in Proc. of IEEE ICASSP, Proc. vol. II, Salt Lake City, May 2001.
 T. Kim and T. Adah, “Nonlinear Satellite Channel Equalization Using Fully Complex FeedForward Neural Networks,” in Proc. of IEEE Workshop on Nonlinear Signal and Image Processing, Baltimore, June, 2001, pp. 141150.
 Title
 Fully Complex MultiLayer Perceptron Network for Nonlinear Signal Processing
 Journal

Journal of VLSI signal processing systems for signal, image and video technology
Volume 32, Issue 12 , pp 2943
 Cover Date
 20020801
 DOI
 10.1023/A:1016359216961
 Print ISSN
 09225773
 Online ISSN
 1573109X
 Publisher
 Kluwer Academic Publishers
 Additional Links
 Topics
 Keywords

 nonlinear adaptive signal processing
 fully complex neural network
 split complex neural network
 elementary transcendental functions
 bounded almost everywhere
 analytic almost everywhere
 Industry Sectors
 Authors

 Taehwan Kim ^{(1)} ^{(2)}
 Tülay Adali ^{(2)}
 Author Affiliations

 1. Center for Advanced Aviation System Development, The MITRE Corporation, M/S N670, 7515 Colshire Drive, McLean, Virginia, 22102, USA
 2. Information Technology Laboratory, Department of Computer Science and Electrical Engineering, University of Maryland Baltimore County, Baltimore, Maryland, 21250, USA