International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064




Downloads: 110 | Views: 124

Research Paper | Mathematics | Sudan | Volume 3 Issue 11, November 2014


A Boundedness of a Batch Gradient Method with Smoothing L_(1?2)Regularization for Pi-sigma Neural Networks

Kh. Sh. Mohamed [2] | Y. Sh. Mohammed [3] | Abd Elmoniem A. Elzain | Mohamed El-Hafiz M. N | and Elnoor. A. A. Noh


Abstract: This paper considers a batch gradient method with L_ (12) regularization for Pi sigma neural networks. In origin, by introducing an L_ (12) regularization term involves absolute value and is not differentiable into the error function. A key point of this paper, specifically, the smoothing L_ (12) regularization is a term proportional to the norm of the weights. The role of the smoothing L_ (12) regularization term is to control the magnitude of the weights and to improve the generalization performance of the networks. The weights are proved to be bounded during the training process, thus the conditions that are required for convergence analysis of batch gradient method in literature are simplified.


Keywords: Batch gradient method, Pi-sigma neural network, L regularization, Boundedness


Edition: Volume 3 Issue 11, November 2014,


Pages: 819 - 825


How to Download this Article?

Type Your Email Address below to Download the Article PDF


How to Cite this Article?

Kh. Sh. Mohamed, Y. Sh. Mohammed, Abd Elmoniem A. Elzain, Mohamed El-Hafiz M. N, and Elnoor. A. A. Noh, "A Boundedness of a Batch Gradient Method with Smoothing L_(1?2)Regularization for Pi-sigma Neural Networks", International Journal of Science and Research (IJSR), Volume 3 Issue 11, November 2014, pp. 819-825, https://www.ijsr.net/get_abstract.php?paper_id=OCT14878



Similar Articles with Keyword 'Boundedness'

Downloads: 113

Research Paper, Mathematics, Sudan, Volume 4 Issue 10, October 2015

Pages: 921 - 922

Conditions of Boundedness and Compactness Sum of Operators on Weighted Berman Space

Eltigani Ismail Hassan [2]

Share this Article

Downloads: 116

Research Paper, Mathematics, Saudi Arabia, Volume 3 Issue 9, September 2014

Pages: 2002 - 2012

Batch Gradient Method with Smoothing L1/2 Regularization and Momentum for Pi-sigma Networks

Kh. Sh. Mohamed [2] | Y. Sh. Mohammed [3] | A. A. Elzain | Kh. M. Makin | Elnoor. A. A. Noh [2]

Share this Article



Top