방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 설명 가능한 순환 신경망× | 설명 가능한 트랜스포머× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2017–2020 | 2017–2021 |
| 창시자≠ | Arrived via XAI literature (Arrieta et al., Lundberg & Lee, and attention-based RNN work) | Vaswani et al. (Transformer); explainability extensions by Chefer et al. and the broader XAI community |
| 유형≠ | Interpretability framework applied to sequence models | Interpretable deep learning model |
| 원전≠ | Arrieta, A. B., Diaz-Rodriguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., Chatila, R., & Herrera, F. (2020). Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI. Information Fusion, 58, 82–115. DOI ↗ | Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30. link ↗ |
| 별칭 | Explainable RNN, Interpretable RNN, XAI-RNN, Transparent Recurrent Neural Network | XAI Transformer, Interpretable Transformer, Transparent Transformer, Explainable Attention Model |
| 관련≠ | 5 | 4 |
| 요약≠ | An Explainable Recurrent Neural Network (XAI-RNN) pairs a standard RNN architecture with a post-hoc or intrinsic interpretability method — such as SHAP, LIME, integrated gradients, or attention visualization — to reveal which input time steps or tokens most influence the model's sequential predictions, without sacrificing predictive accuracy. | An Explainable Transformer combines a standard or pre-trained Transformer architecture with post-hoc or built-in interpretability techniques — such as attention rollout, gradient-weighted attention, or SHAP — to reveal which input tokens or regions drove each prediction. The approach bridges high predictive accuracy with the transparency required in high-stakes or regulated domains. |
| ScholarGate데이터셋 ↗ |
|
|