Machine learningDeep learning / NLP / CV
弱监督 LSTM
弱监督 LSTM 在序列数据上训练长短期记忆（Long Short-Term Memory, LSTM）网络，而这些数据缺乏干净的手动标注标签或完全没有标签。取而代之的是，它结合了多种不完美的标签来源——启发式规则、远程监督、众包或程序化标注函数——来生成概率性训练标签，然后用这些标签来监督 LSTM。这使得在大型无标注语料库上进行可扩展训练成为可能，而无需耗费大量人力进行标注。
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., De Sa, C., Wu, S., Selsam, D., & Re, C. (2016). Data Programming: Creating Large Training Sets, Quickly. Advances in Neural Information Processing Systems (NeurIPS), 29. link ↗
- Zhou, Z.-H. (2018). A brief introduction to weakly supervised learning. National Science Review, 5(1), 44–53. DOI: 10.1093/nsr/nwx106 ↗
如何引用本页
ScholarGate. (2026, June 3). Weakly Supervised Long Short-Term Memory Network. ScholarGate. https://scholargate.app/zh/deep-learning/weakly-supervised-lstm
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.
- 微调长短期记忆网络 (Fine-Tuned LSTM)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
- 半监督长短期记忆网络 (Semi-supervised LSTM)深度学习↔ compare
- 弱监督循环神经网络深度学习↔ compare
- 弱监督 Transformer深度学习↔ compare