Title:

Dynamically-adaptive Weight in Batch Back Propagation Algorithm via Dynamic Training Rate for Speedup and Accuracy Training, Journal of Telecommunications and Information Technology, 2017, nr 4

Creator:

Al_Duais, Mohammed Sarhan ; Mohamad, Fatma Susilawati

Subject and Keywords:

dynamic training rate ; accuracy training ; speed up training ; artificial neural network (ANN) ; batch back propagation algorithm

Description:

The main problem of batch back propagation (BBP) algorithm is slow training and there are several parameters need to be adjusted manually, such as learning rate. In addition, the BBP algorithm suffers from saturation training. The objective of this study is to improve the speed up training of the BBP algorithm and to remove the saturation training. The training rate is the most significant parameter for increasing the efficiency of the BBP. In this study, a new dynamic training rate is created to speed the training of the BBP algorithm. The dynamic batch back propagation (DBBPLR) algorithm is presented, which trains with adynamic training rate. This technique was implemented with a sigmoid function. Several data sets were used as benchmarks for testing the effects of the created dynamic training rate that we created. All the experiments were performed on Matlab. From the experimental results, the DBBPLR algorithm provides superior performance in terms of training, faster training with higher accuracy compared to the BBP algorithm and existing works.

Publisher:

National Institute of Telecommunications

Date:

2017, nr 4

Resource Type:

artykuł

Format:

application/pdf

Resource Identifier:

ISSN 1509-4553, on-line: ISSN 1899-8852

Source:

Journal of Telecommunications and Information Technology

Language:

ang

Rights Management:

Biblioteka Naukowa Instytutu Łączności