ScholarGate
助手
Machine learningDeep learning / NLP / CV

门控循环单元 (GRU)

门控循环单元（Gated Recurrent Unit, GRU）由Cho等人于2014年提出，是一种简化的循环神经网络。它使用两个学习到的门——更新门和重置门——来选择性地保留或丢弃跨时间步的信息，从而以比LSTM更少的参数实现有效的序列建模。

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.

门控循环单元 (GRU)
[需翻译标题：BERT-based Classi…长短期记忆网络（LSTM）循环神经网络领域自适应门控循环单元可解释门控循环单元 (Explainable G…可解释循环神经网络微调门控循环单元 (Fine-Tuned GRU)微调循环神经网络多语言GRU多语言循环神经网络

+10 more

来源

  1. Cho, K., van Merrienboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation. In Proceedings of EMNLP 2014, pp. 1724–1734. link ↗
  2. Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. NIPS 2014 Deep Learning Workshop. link ↗

如何引用本页

ScholarGate. (2026, June 3). Gated Recurrent Unit (GRU). ScholarGate. https://scholargate.app/zh/deep-learning/gated-recurrent-unit

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

领域自适应门控循环单元可解释门控循环单元 (Explainable GRU)可解释循环神经网络微调门控循环单元 (Fine-Tuned GRU)微调循环神经网络长短期记忆网络（LSTM）多语言GRU多语言循环神经网络多模态门控循环单元 (Multimodal GRU)多模态LSTM多模态循环神经网络循环神经网络基于RoBERTa的分类自监督 GRU半监督门控循环单元 (Semi-supervised GRU)LSTM 迁移学习循环神经网络迁移学习弱监督门控循环单元 (Weakly Supervised GRU)弱监督循环神经网络

发现本页有问题？报告或提出修改建议 →

ScholarGate — Gated Recurrent Unit (Gated Recurrent Unit (GRU)). 于 2026-06-15 检索自 https://scholargate.app/zh/deep-learning/gated-recurrent-unit · 数据集： https://doi.org/10.5281/zenodo.20539026