Convergence of Offline Gradient Method with Inner-penalty for Multi-output Feedforward Neural Networks

DOI

10.2991/icmt-13.2013.30How to use a DOI?

Keywords

Feedforward neural networks; Offline gradient method; Inner-penalty; Convergence

Abstract

In this paper, we study an offline gradient method with inner-penalty for training multi-output feedforward neural networks. The monotonicity of the error function and weight boundedness for the offline gradient with inner-penalty are presented, both weak and strong convergence results are proved, which will be very meaningful for theoretical research or applications on multi-output neural networks.

Copyright

© 2013, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Zhou Fengqi
AU  - Liu Ergen
AU  - Xiao Yu
PY  - 2013/11
DA  - 2013/11
TI  - Convergence of Offline Gradient Method with Inner-penalty for Multi-output Feedforward Neural Networks
BT  - Proceedings of 3rd International Conference on Multimedia Technology(ICMT-13)
PB  - Atlantis Press
SP  - 240
EP  - 246
SN  - 1951-6851
UR  - https://doi.org/10.2991/icmt-13.2013.30
DO  - 10.2991/icmt-13.2013.30
ID  - Fengqi2013/11
ER  -