Seunghan Lee

Seunghan Lee

Deep Learning, Data Science, Statistics

Interpretable Deep Learning

[interpretable] (paper 6) Neural Additive Models ; Interpretable Machine Learning with Neural Nets

2 minute read

NAMs

[interpretable] (paper 5) Towards Automatic Concept-based Explanations

1 minute read

Towards Automatic Concept-based Explanations

study(paper 4)uncertainty Aware attention for reliable interpretation and prediction

3 minute read

Attention mechanism

[interpretable] (paper 3) Interpretability Beyond Feature Atribution ; Quantitative Testing with Concept Activation Vectors (TCAV)

5 minute read

TCAV

[interpretable] (paper 2) Grad-CAM ; Visual Explanations from Deep Networks via Gradient-based Localization

3 minute read

Grad-CAM

[interpretable] (paper 1) Why Should I Trust You? Explaining the Predictions of Any Classifier

5 minute read

LIME (Local Interpretable Model-agnostic Explanations)