A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat

Mahat, Norpah (2011) A study of acceleration techniques in training neural networks - local adaptive techniques / Norpah Mahat. Esteem Academic Journal, 7 (2). pp. 35-51. ISSN 1675-7939


Till today, it has been a great challenge in optimizing the training time in neural networks. This paper presents Local Adaptive Techniques and Dynamic Adaptation Methods as acceleration techniques for neural networks. The first technique is based on weight-specific information such as the temporal behavior of the partial derivative of the current weight. The second technique is dynamically adapts the momentum factor, a, and learning rate, ᶯ with respect to the iteration number or gradient. Some of the most popular learning algorithms are described and discussed. Simulations on a real world application problem are conducted to evaluate and compare the performance of a local adaptive strategies with various popular training algorithms include global adaptive strategies. These techniques have been compared and measured in terms of
gradient and error function evaluations, and percentage of success.


Item Type: Article
Email / ID Num.
Mahat, Norpah
Subjects: Q Science > QA Mathematics > Instruments and machines > Electronic Computers. Computer Science
Divisions: Universiti Teknologi MARA, Shah Alam > Faculty of Computer and Mathematical Sciences
Journal or Publication Title: Esteem Academic Journal
UiTM Journal Collections: UiTM Journal > ESTEEM Academic Journal (EAJ)
ISSN: 1675-7939
Volume: 7
Number: 2
Page Range: pp. 35-51
Keywords: Neural Networks, Local Adaptive Techniques, Dynamic Adaptation Methods
Date: 2011
URI: https://ir.uitm.edu.my/id/eprint/8852
Edit Item
Edit Item


[thumbnail of AJ_NORPAH MAHAT ESTEEM 11.pdf] Text

Download (0B)

ID Number




Statistic details