ScholarGate
助手
Machine learningDeep learning / NLP / CV

循环神经网络

循环神经网络(Recurrent Neural Network, RNN)是一种旨在通过维护一个在时间步之间传递信息的隐藏状态来处理序列数据的神经网络。其现代形式由Rumelhart等人于1986年提出,并由Elman于1990年进一步完善。在基于注意力机制的模型兴起之前,RNN曾是自然语言处理、语音识别和时间序列分析中序列建模的主导架构。

在 MethodMind 中打开即将推出视频即将推出Download slides

阅读完整方法

仅限会员

使用免费账户登录即可阅读本节。

登录

Method map

The neighbourhood of related methods — select a node to explore.

+15 more

来源

  1. Elman, J. L. (1990). Finding structure in time. Cognitive Science, 14(2), 179–211. DOI: 10.1207/s15516709cog1402_1
  2. Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533–536. DOI: 10.1038/323533a0

如何引用本页

ScholarGate. (2026, June 3). Recurrent Neural Network (RNN). ScholarGate. https://scholargate.app/zh/deep-learning/recurrent-neural-network

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

被引用于

ScholarGateRecurrent Neural Network (Recurrent Neural Network (RNN)). 于 2026-06-15 检索自 https://scholargate.app/zh/deep-learning/recurrent-neural-network · 数据集: https://doi.org/10.5281/zenodo.20539026