So sánh phương pháp
Xem các phương pháp đã chọn cạnh nhau; những hàng khác biệt được làm nổi bật.
| GRU có thể giải thích được× | Mạng bộ nhớ dài-ngắn hạn (LSTM)× | |
|---|---|---|
| Lĩnh vực | Học sâu | Học sâu |
| Họ | Machine learning | Machine learning |
| Năm ra đời≠ | 2014 (GRU); 2016–2017 (XAI integration) | 1997 |
| Người khởi xướng≠ | Cho, K. et al. (GRU); explainability layer via Lundberg & Lee (SHAP) and Ribeiro et al. (LIME) | Hochreiter, S. & Schmidhuber, J. |
| Loại≠ | Recurrent neural network with post-hoc or attention-based interpretability | Recurrent neural network with gated memory cells |
| Công trình gốc≠ | 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 ↗ | Hochreiter, S. & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735–1780. DOI ↗ |
| Tên gọi khác | XAI-GRU, Interpretable GRU, GRU with explainability, Transparent GRU | LSTM, LSTM network, LSTM-RNN, long short-term memory RNN |
| Liên quan≠ | 5 | 4 |
| Tóm tắt≠ | Explainable GRU pairs the Gated Recurrent Unit, a compact and efficient recurrent architecture, with explainability techniques such as SHAP, LIME, or attention weighting to reveal which time steps and features drove each prediction. It brings interpretability to sequential modelling without sacrificing the GRU's ability to capture temporal dependencies. | Long Short-Term Memory (LSTM) is a gated recurrent neural network architecture introduced by Hochreiter and Schmidhuber in 1997. It was designed to learn dependencies across long sequences by using dedicated memory cells and three learned gates — forget, input, and output — that control what information is retained, updated, or passed forward at each time step. |
| ScholarGateBộ dữ liệu ↗ |
|
|