Convergence of an online split-complex gradient algorithm for complex-valued neural networks.

Zhang, Huisheng; Xu, Dongpo; Wang, Zhiping

Discrete Dynamics in Nature and Society (2010)

  • Volume: 2010, page Article ID 829692, 27 p.-Article ID 829692, 27 p.
  • ISSN: 1026-0226

How to cite

top

Zhang, Huisheng, Xu, Dongpo, and Wang, Zhiping. "Convergence of an online split-complex gradient algorithm for complex-valued neural networks.." Discrete Dynamics in Nature and Society 2010 (2010): Article ID 829692, 27 p.-Article ID 829692, 27 p.. <http://eudml.org/doc/230731>.

@article{Zhang2010,
author = {Zhang, Huisheng, Xu, Dongpo, Wang, Zhiping},
journal = {Discrete Dynamics in Nature and Society},
keywords = {online gradient method; adaptive learning},
language = {eng},
pages = {Article ID 829692, 27 p.-Article ID 829692, 27 p.},
publisher = {Hindawi Publishing Corporation, New York},
title = {Convergence of an online split-complex gradient algorithm for complex-valued neural networks.},
url = {http://eudml.org/doc/230731},
volume = {2010},
year = {2010},
}

TY - JOUR
AU - Zhang, Huisheng
AU - Xu, Dongpo
AU - Wang, Zhiping
TI - Convergence of an online split-complex gradient algorithm for complex-valued neural networks.
JO - Discrete Dynamics in Nature and Society
PY - 2010
PB - Hindawi Publishing Corporation, New York
VL - 2010
SP - Article ID 829692, 27 p.
EP - Article ID 829692, 27 p.
LA - eng
KW - online gradient method; adaptive learning
UR - http://eudml.org/doc/230731
ER -

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.