Facebook pixel tracking

The Science and Information (SAI) Organization publishes open-access peer-reviewed journals in computer science and artificial intelligence.

Contact Info
Email info@thesai.org
Website thesai.org
Follow Us
Contact Info
Email info@thesai.org
Follow Us
Research Article | Open Access |

Natural Gradient Descent for Training Stochastic Complex-Valued Neural Networks

Author 1: Tohru Nitta
International Journal of Advanced Computer Science and Applications (IJACSA) · Vol. 5, No. 7 · Published 2014 · Cited by 8

DOI: https://doi.org/10.14569/IJACSA.2014.050729

Download PDF Cite Call for Papers

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.

Keywords

Neural network Complex number Learning Singular point

How to Cite this Article

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

Nitta, Tohru. "Natural Gradient Descent for Training Stochastic Complex-Valued Neural Networks." International Journal of Advanced Computer Science and Applications, vol. 5, no. 7, 2014, https://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},
  volume    = {5},
  number    = {7},
  year      = {2014},
  publisher = {The Science and Information Organization},
  author    = {Tohru Nitta},
  doi       = {10.14569/IJACSA.2014.050729},
  url       = {https://doi.org/10.14569/IJACSA.2014.050729}
}

Open Access — licensed under a Creative Commons Attribution 4.0 International License. Unrestricted use, distribution, and reproduction in any medium, even commercially, as long as the original work is properly cited.

Back to Issue
IJACSA Journal Cover

IJACSA