방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 설명 가능한 다층 퍼셉트론× | 설명 가능한 LSTM (Explainable LSTM)× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2010s–present | 2017–2019 |
| 창시자≠ | Lundberg & Lee (SHAP); Ribeiro et al. (LIME); broader XAI community | Lundberg & Lee (SHAP); Ribeiro et al. (LIME); community synthesis |
| 유형≠ | Supervised feedforward neural network with interpretability layer | Interpretable deep learning (post-hoc explainability) |
| 원전 | Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774. link ↗ | Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, 30, 4765–4774. link ↗ |
| 별칭 | XMLP, Interpretable MLP, Explainable feedforward neural network, Transparent MLP | XAI-LSTM, interpretable LSTM, LSTM with SHAP, transparent LSTM |
| 관련≠ | 4 | 5 |
| 요약≠ | An Explainable Multilayer Perceptron (XMLP) is a standard feedforward neural network trained with backpropagation, augmented with post-hoc interpretability techniques — such as SHAP values, LIME, or integrated gradients — that attribute each prediction to individual input features. The combination retains the MLP's approximation power while satisfying transparency requirements common in regulated or high-stakes domains. | Explainable LSTM pairs a trained Long Short-Term Memory network with post-hoc interpretability techniques — chiefly SHAP, LIME, integrated gradients, or attention visualization — to reveal which time steps, tokens, or features drive each prediction. It bridges the accuracy of recurrent deep learning with the transparency demanded by high-stakes domains such as clinical decision support, fraud detection, and regulatory compliance. |
| ScholarGate데이터셋 ↗ |
|
|