Full-Text Search:
Home|Journal Papers|About CNKI|User Service|FAQ|Contact Us|中文
Add to Favorite Get Latest Update

A New Method for Training RNN via Hidden Representation Estimated by EM Algorithm

DAI Xian hua (Dept.of Electronic Eng.,Shantou University,Shantou 515063,China)  
A new method for training recurrent neural network (RNN) has been proposed.By introducing the hidden representation or hidden variables into RNN,training the complicated RNN is decomposed into training a set of single neurons and a linear output layer.Based on linear approximation of RNN hidden units,RNN is remodeled with a “mixture of experts”(ME) model.Morever,training RNN is also changed into a maximum likelihood estimation of the linear systems with hidden variables.Finally,training RNN is fulfilled with the expectation maximization (EM) algorithm.
【Fund】: 国家自然科学基金!(No.69872 0 2 1 );; 广东省自然科学基金!(No .980 4 38)
【CateGory Index】: TP18
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©2006 Tsinghua Tongfang Knowledge Network Technology Co., Ltd.(Beijing)(TTKN) All rights reserved