MLI for Regular (Non-Time-Series) Experiments

This section describes MLI functionality and features for regular experiments. Refer to MLI for Time-Series Experiments for MLI information with time-series experiments.

• Interpret a model
  • Interpret a Driverless AI model
  • Interpreting Predictions From an External Model
  • Explainer Recipes
  • Interpretation Expert Settings
• Interpretation Expert Settings
  • MLI Tab
  • MLI NLP Tab
  • MLI Surrogate Models Tab
• Explainer (Recipes) Expert Settings
  • Absolute Permutation Feature Importance Explainer Settings
  • MLI AutoDoc Explainer Settings
  • Disparate Impact Analysis Explainer Settings
  • NLP Partial Dependence Plot Explainer Settings
  • NLP Vectorizer + Linear Model Text Feature Importance Explainer Settings
  • Partial Dependence Plot Explainer Settings
  • Sensitivity Analysis Explainer Settings
  • Shapley Summary Plot Explainer Settings
  • Shapley Values for Original Features Settings
  • Surrogate Decision Tree Explainer Settings
• Understanding the Model Interpretation Page
  • Summary Tab
  • Interpretations Using Driverless AI Model (DAI Model Tab)
  • Interpretations Using Surrogate Model (Surrogate Model Tab)
  • Interpretations Using NLP Dataset (NLP Tab)
  • MLI Dashboard
  • The Task Bar
  • DAI Model Plots
  • Surrogate Model Plots
  • NLP Plots
• Viewing Explanations
• General Considerations
  • Machine Learning and Approximate Explanations
  • The Multiplicity of Good Models in Machine Learning
  • Expectations for Consistency Between Explanatory Techniques