点击次数：

论文类型：会议论文

发表时间：2007-06-03

收录刊物：CPCI-S、EI

卷号：4493

期号：PART 3

页面范围：117-+

摘要：Probabilistic convergence results of online gradient descent algorithm have been obtained by many authors for the training of recurrent neural networks with innitely many training samples. This paper proves deterministic convergence of o2ine gradient descent algorithm for a recurrent neural network with nite number of training samples. Our results can be hopefully extended to more complicated recurrent neural networks, and serve as a complementary result to the existing probability convergence results.