Machine learningDeep learning / NLP / CV
可解释门控循环单元 (Explainable GRU)
可解释门控循环单元 (Explainable GRU) 将门控循环单元 (Gated Recurrent Unit, GRU)——一种简洁高效的循环架构——与 SHAP、LIME 或注意力权重等可解释性技术相结合，以揭示是哪些时间步和特征驱动了每次预测。它在不牺牲 GRU 捕捉时间依赖性的能力的前提下，为序列建模带来了可解释性。
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
- 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. Proceedings of EMNLP 2014, 1724–1734. DOI: 10.3115/v1/D14-1179 ↗
- Lundberg, S. M., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems (NeurIPS), 30, 4765–4774. link ↗
如何引用本页
ScholarGate. (2026, June 3). Explainable Gated Recurrent Unit. ScholarGate. https://scholargate.app/zh/deep-learning/explainable-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.
- 可解释长短期记忆网络深度学习↔ compare
- 可解释循环神经网络深度学习↔ compare
- 可解释 Transformer深度学习↔ compare
- 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