Explainable AI Recipes: Implement Solutions to Model Explainability and Interpretability with Python

Index

A

Artificial intelligence (AI)

B

Backpropagation neural networks

Bagging

Boosting

C

Captum

Catboost model

Causal factors

Classical predictive modeling

Classification model

Convolutional neural network layer

D

Decision tree classification model

Decision tree model

Deep learning (DL)

kernel-based explainer, Keras

MNIST

PyTorch

sequential information processing

Deep neural network models

Descent-based boosting model

E, F

ELI5 library

ELI5 permutation library

Ensemble models

bagging

catboost model

catboost model interpretation

classification model

EBM

EBM classifier

ELI5 explainer

ELI5 permutation library

extreme gradient boosting–based regressor

global feature importance

global/local explainable libraries

LIME explainer

mixed input feature data, SHAP

multiclass classification problems ...