Bidirectional recurrent neural networks
Bidirectional recurrent neural networks
复制标题
DOI：
10.1109/78.650093
复制
发表时间：
1997-11-01
影响因子：
5.4
通讯作者：
Paliwal, KK
中科院分区：
文献类型：
--
作者：
Schuster, M;Paliwal, KK
在本文的第一部分中，一个规则的递归神经网络（RNN）扩展到一个双向递归神经网络（BRNN）。BRNN可以在不限制使用输入信息的情况下训练到预设的未来帧。这是通过在正、负时间方向上同时训练网络来实现的，并对网络的结构和训练过程进行了说明。在人工数据的回归和分类实验中，所提出的结构给出了更好的结果比其他方法。对于真实的数据，从TIMIT数据库音素的分类实验显示出相同的trends.In本文的第二部分，它是如何建议的双向结构可以很容易地修改，允许有效地估计完整的符号序列的条件后验概率，而不作任何明确的假设的形状的分布。在这一部分中，我们用真实的数据进行了实验。
In the first part of this paper, a regular recurrent neural network (RNN) is extended to a bidirectional recurrent neural network (BRNN). The BRNN can be trained without the limitation of using input information just up to a preset future frame. This is accomplished by training it simultaneously in positive and negative time direction, Structure and training procedure of the proposed network are explained. In regression and classification experiments on artificial data, the proposed structure gives better results than other approaches. For real data, classification experiments for phonemes from the TIMIT database show the same tendency.In the second part of this paper, it is shown how the proposed bidirectional structure can be easily modified to allow efficient estimation of the conditional posterior probability of complete symbol sequences without making any explicit assumption about the shape of the distribution. For this part, experiments on real data are reported.