Abstract
The complex-valued learning algorithms described in the chapters 2 and 3 use a real-valued mean square error function as the performance measure which explicitly minimizes only the magnitude error. In addition, the mean squared error function is non-analytic in the Complex domain (not differentiable in an open set).
An Erratum for this chapter can be found at http://dx.doi.org/10.1007/978-3-642-29491-4_9
An erratum to this chapter can be found at http://dx.doi.org/10.1007/978-3-642-29491-4_9
Access provided by Autonomous University of Puebla. Download to read the full chapter text
Chapter PDF
References
Savitha, R., Suresh, S., Sundararajan, N., Saratchandran, P.: A new learning algorithm with logarithmic performance index for complex-valued neural networks. Neurocomputing 72(16-18), 3771–3781 (2009)
Wirtinger, W.: Zur formalen theorie der funktionen von mehr komplexen vernderlichen. Annals of Mathematics 97 (1927)
Yu, S.-S., Tsai, W.-H.: Relaxation by the Hopfield neural network. Pattern Recognition 25(2), 197–209 (1992)
Loss, D.V., de Castro, M.C.F., Franco, P.R.G., de Castro, E.C.C.: Phase transmittance RBF neural networks. Electronics Letters 43(16), 882–884 (2007)
Remmert, R.: Theory of Complex Functions. Springer, New York (1991)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
Copyright information
© 2013 Springer-Verlag GmbH Berlin Heidelberg
About this chapter
Cite this chapter
Suresh, S., Sundararajan, N., Savitha, R. (2013). Fully Complex-valued Relaxation Networks. In: Supervised Learning with Complex-valued Neural Networks. Studies in Computational Intelligence, vol 421. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-29491-4_4
Download citation
DOI: https://doi.org/10.1007/978-3-642-29491-4_4
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-29490-7
Online ISBN: 978-3-642-29491-4
eBook Packages: EngineeringEngineering (R0)