Machine learningDeep learning / NLP / CV
弱监督门控循环单元 (Weakly Supervised GRU)
弱监督门控循环单元 (Weakly Supervised GRU) 在由不完美、启发式或程序化来源标记的序列上训练门控循环单元 (GRU) 网络，而不是依赖昂贵的手工标注真实标签。它将 GRU 在捕捉时间依赖性方面的效率与弱监督技术相结合，后者用于聚合噪声标签，从而在缺乏大规模完全标注数据集的情况下实现实用的序列建模。
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
- Ratner, A. J., De Sa, C. M., Wu, S., Selsam, D., & Re, C. (2016). Data Programming: Creating Large Training Sets, Quickly. Advances in Neural Information Processing Systems (NeurIPS), 29. link ↗
- Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. NIPS 2014 Workshop on Deep Learning. link ↗
如何引用本页
ScholarGate. (2026, June 3). Weakly Supervised Gated Recurrent Unit Network. ScholarGate. https://scholargate.app/zh/deep-learning/weakly-supervised-gru
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.
- 门控循环单元 (GRU)深度学习↔ compare
- 长短期记忆网络（LSTM）深度学习↔ compare
- 循环神经网络深度学习↔ compare
- 半监督门控循环单元 (Semi-supervised GRU)深度学习↔ compare
- 弱监督 LSTM深度学习↔ compare
- 弱监督 Transformer深度学习↔ compare