Tutorials & Example Code
Basics
Applications
- DataAnalyzer for feature analysis
- TabularExplainer for income prediction (classification)
- TabularExplainer for house-price prediction (regression)
- VisionExplainer for image classification
- NLPExplainer for sentiment analysis
- NLPExplainer on IMDB dataset
- TimeseriesExplainer for time series anomaly detection
- OmniXAI in a ML workflow
Tabular Explainers
- Accumulated local effects (ALE)
- Counterfactual explanation on Diabetes dataset
- GPT explainer for income prediction
- L2X (learning to explain) for income prediction
- LIME for income prediction
- Logistic regression for income prediction
- MACE counterfactual explanation for income prediction
- Paritial dependence plots (PDP)
- Learning to Rank Expanations Demo
- Morris sensitivity analysis
- SHAP for income prediction
- Decision tree for income prediction
Vision Explainers
- Counterfactual explanation on ImageNet
- Counterfactual explanation on MNIST (Tensorflow)
- Counterfactual explanation on MNIST (PyTorch)
- Contrastive explanation on MNIST (Tensorflow)
- Contrastive explanation on MNIST (PyTorch)
- Feature map visualization (Tensorflow)
- Feature map visualization (PyTorch)
- Feature visualization (Tensorflow)
- Feature visualization (PyTorch)
- Grad-CAM for image classification (Tensorflow)
- Grad-CAM for image classification (PyTorch)
- Grad-CAM for visual language tasks
- Integrated-gradient for image classification (Tensorflow)
- Integrated-gradient for image classification (PyTorch)
- Integrated-gradient for visual language tasks
- L2X (learning to explain) on MNIST
- LIME for image classification
- SHAP on MNIST
NLP Explainers
- Counterfactual explanation for text classification
- Counterfactual explanation for question answering
- Integrated-gradient on IMDB dataset (Tensorflow)
- Integrated-gradient on IMDB dataset (PyTorch)
- L2X (learning to explain) for text classification
- LIME for text classification
- SHAP for sentiment analysis