TY - GEN
T1 - Improvements of coefficient learning in BPNN for image restoration
AU - Duan, Yonghao
AU - Zhao, Peng
AU - Sun, Yuming
AU - Zhao, Sanyuan
PY - 2012
Y1 - 2012
N2 - In this paper, we propose a method dealing with the problem of image restoration based on the conception of Back propagation Neural Network Algorithm. Conventional Back Propagation Algorithm has its inherited drawbacks, i.e. slow convergence rate, long training time, hard to achieve global minima etc. Recently, several methods introduced the dynamic learning rate and the dynamic momentum coefficient. Our new method applied in this paper improves the effect of learning coefficient η by using a new way to modify the value dynamically. The experimental results show that this helps improving the efficiency overall both in visual effect and quality analysis.
AB - In this paper, we propose a method dealing with the problem of image restoration based on the conception of Back propagation Neural Network Algorithm. Conventional Back Propagation Algorithm has its inherited drawbacks, i.e. slow convergence rate, long training time, hard to achieve global minima etc. Recently, several methods introduced the dynamic learning rate and the dynamic momentum coefficient. Our new method applied in this paper improves the effect of learning coefficient η by using a new way to modify the value dynamically. The experimental results show that this helps improving the efficiency overall both in visual effect and quality analysis.
KW - Back Propagation Neural Network
KW - Dynamic Learning Coefficient
KW - Image Restoration
KW - Neural Networks
UR - https://www.scopus.com/pages/publications/84864245178
U2 - 10.1109/ICSAI.2012.6223609
DO - 10.1109/ICSAI.2012.6223609
M3 - Conference contribution
AN - SCOPUS:84864245178
SN - 9781467301992
T3 - 2012 International Conference on Systems and Informatics, ICSAI 2012
SP - 2692
EP - 2694
BT - 2012 International Conference on Systems and Informatics, ICSAI 2012
T2 - 2012 International Conference on Systems and Informatics, ICSAI 2012
Y2 - 19 May 2012 through 20 May 2012
ER -