Abstract
This paper presents some results of an analysis on the decision boundaries of complex-valued neurons. The main results may be summarized as follows. (a) Weight parameters of a complex-valued neuron have a restriction which is concerned with two-dimensional motion. (b) The decision boundary of a complex-valued neuron consists of two hypersurfaces which intersect orthogonally, and divides a decision region into four equal sections.
Similar content being viewed by others
References
Benvenuto, N. and Piazza, F.: On the complex backpropagation algorithm, IEEE Trans. Sig. Proc. 40 (1992), 967-969.
Georgiou, G. M. and Koutsougeras, C.: Complex domain backpropagation, IEEE Trans. Circ. Syst.-II: Analog Dig. Sig. Proc. 39 (1992), 330-334.
Hirose, A.: Proposal of fully complex-valued neural networks, Proc. Internat. Joint Conf. Neural Networks, Vol. 4, 1992, pp. 152-157.
Kim, M. S. and Guest, C. C.: Modification of backpropagation networks for complex-valued signal processing in frequency domain, Proc. Internat. Joint Conf. Neural Networks, Vol. 3, June 1990, pp. 27-31.
Lippmann, R. P.: An introduction to computing with neural nets, IEEE Acoustic, Speech and Signal Processing Magazine, April 1987, 4-22.
Nitta, T. and Furuya, T.: A complex back-propagation learning, Trans. Information Proc. Soc. Japan 32 (1991), 1319-1329 (in Japanese).
Nitta, T.: A complex numbered version of the back-propagation algorithm, Proc. INNS World Cong. Neural Networks, Portland, Vol. 3, July 1993, pp. 576-579.
Nitta, T.: An extension of the back-propagation algorithm to complex numbers, Neural Networks 10 (1997), 1392-1415.
Rumelhart, D. E. et al.: Parallel Distributed Processing, Vol. 1, MIT Press, 1986.
Author information
Authors and Affiliations
Rights and permissions
About this article
Cite this article
Nitta, T. An Analysis of the Fundamental Structure of Complex-Valued Neurons. Neural Processing Letters 12, 239–246 (2000). https://doi.org/10.1023/A:1026582217675
Issue Date:
DOI: https://doi.org/10.1023/A:1026582217675