TY - GEN
T1 - Improving the Quickprop algorithm
AU - Cheung, Chi Chung
AU - Ng, Sin Chun
AU - Lui, Andrew K.
PY - 2012/6/10
Y1 - 2012/6/10
N2 - Backpropagation (BP) algorithm is the most popular supervised learning algorithm that is extensively applied in training feed-forward neural networks. Many BP modifications have been proposed to increase the convergence rate of the standard BP algorithm, and Quickprop is one the most popular fast learning algorithms. The convergence rate of Quickprop is very fast; however, it is easily trapped into a local minimum and thus it cannot converge to the global minimum. This paper proposes a new fast learning algorithm modified from Quickprop. By addressing the drawbacks of the Quickprop algorithm, the new algorithm has a systematic approach to improve the convergence rate and the global convergence capability of Quickprop. Our performance investigation shows that the proposed algorithm always converges with a faster learning rate compared with Quickprop. The improvement in the global convergence capability is especially large. In one learning problem (application), the global convergence capability increased from 4% to 100%.
AB - Backpropagation (BP) algorithm is the most popular supervised learning algorithm that is extensively applied in training feed-forward neural networks. Many BP modifications have been proposed to increase the convergence rate of the standard BP algorithm, and Quickprop is one the most popular fast learning algorithms. The convergence rate of Quickprop is very fast; however, it is easily trapped into a local minimum and thus it cannot converge to the global minimum. This paper proposes a new fast learning algorithm modified from Quickprop. By addressing the drawbacks of the Quickprop algorithm, the new algorithm has a systematic approach to improve the convergence rate and the global convergence capability of Quickprop. Our performance investigation shows that the proposed algorithm always converges with a faster learning rate compared with Quickprop. The improvement in the global convergence capability is especially large. In one learning problem (application), the global convergence capability increased from 4% to 100%.
UR - http://www.scopus.com/inward/record.url?scp=84865104511&partnerID=8YFLogxK
U2 - 10.1109/IJCNN.2012.6252546
DO - 10.1109/IJCNN.2012.6252546
M3 - Conference article published in proceeding or book
AN - SCOPUS:84865104511
SN - 9781467314909
T3 - Proceedings of the International Joint Conference on Neural Networks
BT - 2012 International Joint Conference on Neural Networks, IJCNN 2012
T2 - 2012 Annual International Joint Conference on Neural Networks, IJCNN 2012, Part of the 2012 IEEE World Congress on Computational Intelligence, WCCI 2012
Y2 - 10 June 2012 through 15 June 2012
ER -