01_​Explainable_​Artificial_​Intelligence_​(XAI)_​Simple

0 ×

This application is a simple example of AutoML with KNIME Software for binary and multiclass classification. The output models are then explained via the interactive XAI View, which works for any model the AutoML component produces. Machine Learning Interpretability (MLI) techniques used: SHAP explanations/reason codes, partial dependence, individual conditional expectation (ICE) curves and a surrogate decision tree.

The workflow also works locally on KNIME Analytics Platform. Make sure to use "Apply and Close" in bottom-right corner of each view.

Nodes

• Column Filter110 ×
• Component Input75 ×
• Component Output75 ×
• Rule Engine Variable72 ×
• Column Rename69 ×
• Show all 139 nodes

Extensions

• FeatureKNIME Base nodes
• FeatureKNIME Data Generation
• FeatureKNIME Deep Learning - Keras Integration
• FeatureKNIME Ensemble Learning Wrappers
• FeatureKNIME H2O Machine Learning Integration
• FeatureKNIME Integrated Deployment
• FeatureKNIME JavaScript Views
• FeatureKNIME Javasnippet
• FeatureKNIME Machine Learning Interpretability Extension
• FeatureKNIME Math Expression (JEP)
• FeatureKNIME Optimization extension
• FeatureKNIME PMML Preprocessing Applier Nodes
• FeatureKNIME Quick Forms
• FeatureKNIME XGBoost Integration

Links

• KNIME Integrated Deployment - KNIME.com

  www.knime.com/integrated-deployment
• AutoML Component - KNIME Hub

  kni.me/c/33fQGaQzuZByy6hE
• XAI View Component - KNIME Hub

  kni.me/c/no0cArkQ94BnNpeb
• Interpretable Machine Learning - Christoph Molnar - 2020-09-28

  christophm.github.io/interpretable-ml-book/
• Explainable artificial intelligence - WIkipedia

  en.wikipedia.org/wiki/Explainable_artificial_intelligence