Abstract: In this paper, the natural gradient descent method for the multilayer stochastic complex-valued neural networks is considered, and the natural gradient is given for a single stochastic complex-valued neuron as an example. Since the space of the learnable parameters of stochastic complex-valued neural networks is not the Euclidean space but a curved manifold, the complex-valued natural gradient method is expected to exhibit excellent learning performance.

Tohru Nitta, “Natural Gradient Descent for Training Stochastic Complex-Valued Neural Networks” International Journal of Advanced Computer Science and Applications(IJACSA), 5(7), 2014. http://dx.doi.org/10.14569/IJACSA.2014.050729

@article{Nitta2014,
title = {Natural Gradient Descent for Training Stochastic Complex-Valued Neural Networks},
journal = {International Journal of Advanced Computer Science and Applications},
doi = {10.14569/IJACSA.2014.050729},
url = {http://dx.doi.org/10.14569/IJACSA.2014.050729},
year = {2014},
publisher = {The Science and Information Organization},
volume = {5},
number = {7},
author = {Tohru Nitta}
}