The Computational Power of Complex-Valued Neuron
- 950 Downloads
There exist some problems that cannot be solved with conventional usual 2-layered real-valued neural networks (i.e., a single realvalued neuron) such as the XOR problem and the detection of symmetry. In this paper, it will be proved that such problems can be solved by a 2-layered complex-valued neural network (i.e., a single complex-valued neuron) with the orthogonal decision boundaries. Furthermore, it will be shown that the fading equalization problem can be successfully solved by the 2-layered complex-valued neural network with the highest generalization ability.
Unable to display preview. Download preview PDF.
- 2.Nitta, T., Furuya, T.: A Complex Back-propagation Learning. Transactions of Information Processing Society of Japan, 32(10), (1991) 1319–1329 (in Japanese)Google Scholar
- 4.Nitta, T.: An Analysis on Fundamental Structure of Complex-valued Neuron. Neural Processing Letters, 12(3), (2000) 239–246Google Scholar
- 5.Nitta, T.: Submitted to a journal (2003)Google Scholar
- 6.Rumelhart, D. E., Hinton, G. E., Williams, R. J.: Parallel Distributed Processing (Vol. 1). MIT Press (1986)Google Scholar