MLI Overview

Driverless AI provides robust interpretability of machine learning models to explain modeling results in a human-readable format. In the Machine Learning Interpetability (MLI) view, Driverless AI employs a host of different techniques and methodologies for interpreting and explaining the results of its models. A number of charts are generated automatically (depending on experiment type), including K-LIME, Shapley, Variable Importance, Decision Tree Surrogate, Partial Dependence, Individual Conditional Expectation, Sensitivity Analysis, NLP Tokens, NLP LOCO, and more. Additionally, you can download a CSV of LIME and Shapley reasons codes from this view.

This chapter describes Machine Learning Interpretability (MLI) in Driverless AI for both regular and time-series experiments. Refer to the following sections for more information:

• The Interpreted Models Page

• MLI for Regular (Non-Time-Series) Experiments

• MLI for Time-Series Experiments

Additional Resources

• Click here to download our MLI cheat sheet.

• “An Introduction to Machine Learning Interpetability” book.

• Click here to access the H2O.ai MLI Resources repository. This repo includes materials that illustrate applications or adaptations of various MLI techniques for practicing data scientists.

• Click here to view our H2O Driverless AI Machine Learning Interpretability walkthrough video.

Limitations

• This release deprecates experiments run in 1.7.0 and earlier. MLI will not be available for experiments from versions <= 1.7.0.

• MLI is not supported for multiclass Time Series experiments.

• MLI does not require an Internet connection to run on current models.