A backpropagation algorithm with adaptive learning rate and momentum coefficient

Chien Cheng Yu, Bin-Da Liu

研究成果: Paper同行評審

97 引文 斯高帕斯(Scopus)

摘要

Slower convergence and longer training times are the disadvantages often mentioned when the conventional back-propagation (BP) algorithm are compared with other competing techniques. In addition, in the conventional BP algorithm, the learning rate is fixed and that it is uniform for all weights in a layer. In this paper, we propose an efficient acceleration technique -BPALM (Back-Propagation with Adaptive Learning rate and Momentum term), which is based on the conventional BP algorithm by employing an adaptive learning rate and momentum factor, where the learning rate and the momentum rate are adjusted at each iteration, to reduce the training time is presented. Simulation results indicate a superior convergence speed as compared to other competing methods.

原文English
頁面1218-1223
頁數6
出版狀態Published - 2002 一月 1
事件2002 International Joint Conference on Neural Networks (IJCNN '02) - Honolulu, HI, United States
持續時間: 2002 五月 122002 五月 17

Other

Other2002 International Joint Conference on Neural Networks (IJCNN '02)
國家/地區United States
城市Honolulu, HI
期間02-05-1202-05-17

All Science Journal Classification (ASJC) codes

  • 軟體
  • 人工智慧

指紋

深入研究「A backpropagation algorithm with adaptive learning rate and momentum coefficient」主題。共同形成了獨特的指紋。

引用此