IMPROVED BACKPROPAGATION LEARNING IN NEURAL NETWORKS WITH WINDOWED MOMENTUM

  • ERNEST ISTOOK
    Brigham Young University, Computer Science Department, 3361 TMCB, P.O. Box 26576, Provo Utah 84602-6576, USA
  • TONY MARTINEZ
    Brigham Young University, Computer Science Department, 3361 TMCB, P.O. Box 26576, Provo Utah 84602-6576, USA

書誌事項

公開日
2002-06
DOI
  • 10.1142/s0129065702001114
公開者
World Scientific Pub Co Pte Lt

この論文をさがす

説明

<jats:p> Backpropagation, which is frequently used in Neural Network training, often takes a great deal of time to converge on an acceptable solution. Momentum is a standard technique that is used to speed up convergence and maintain generalization performance. In this paper we present the Windowed Momentum algorithm, which increases speedup over Standard Momentum. Windowed Momentum is designed to use a fixed width history of recent weight updates for each connection in a neural network. By using this additional information, Windowed Momentum gives significant speedup over a set of applications with same or improved accuracy. Windowed Momentum achieved an average speedup of 32% in convergence time on 15 data sets, including a large OCR data set with over 500,000 samples. In addition to this speedup, we present the consequences of sample presentation order. We show that Windowed Momentum is able to overcome these effects that can occur with poor presentation order and still maintain its speedup advantages. </jats:p>

収録刊行物

被引用文献 (1)*注記

もっと見る

詳細情報 詳細情報について

問題の指摘

ページトップへ