The Computational Power of Complex-Valued Neuron
暂无分享,去创建一个
There exist some problems that cannot be solved with conventional usual 2-layered real-valued neural networks (i.e., a single real-valued 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.
[1] James L. McClelland,et al. Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .
[2] Tohru Nitta,et al. An Extension of the Back-Propagation Algorithm to Complex Numbers , 1997, Neural Networks.
[3] Tohru Nitta. An Analysis of the Fundamental Structure of Complex-Valued Neurons , 2004, Neural Processing Letters.