Machine learning
双向循环神经网络
双向循环神经网络（Bidirectional RNN）由Schuster和Paliwal于1997年提出，它以正向和反向两个方向处理序列，从而使每个位置都能访问其完整的周围上下文。结合长短期记忆（LSTM）或门控循环单元（GRU）细胞（即BiLSTM/BiGRU），它已成为命名实体识别、序列标注和语音识别领域的标准方法。
阅读完整方法
仅限会员
登录使用免费账户登录即可阅读本节。
Method map
The neighbourhood of related methods — select a node to explore.
来源
- Schuster, M. & Paliwal, K.K. (1997). Bidirectional Recurrent Neural Networks. IEEE Transactions on Signal Processing, 45(11), 2673–2681. DOI: 10.1109/78.650093 ↗
- Graves, A. & Schmidhuber, J. (2005). Framewise Phoneme Classification with Bidirectional LSTM Networks. IJCNN, 2047–2052. DOI: 10.1109/IJCNN.2005.1556215 ↗
如何引用本页
ScholarGate. (2026, June 1). Bidirectional Recurrent Neural Network (BiLSTM / BiGRU). ScholarGate. https://scholargate.app/zh/deep-learning/bidirectional-rnn
Which method?
Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.
Compare side by side →