Training schedule
IN-COMPANY TRAINING PROGRAMS
Contact Giovanni Lanzani, if you want to know more about custom data & AI training for your teams. He’ll be happy to help you!
Check out more
Get a toolbox of interpretability techniques that you can use in your daily work, understanding when and how you can and should use it.
Start by applying techniques based on implementations from popular packages and what their drawbacks are, to prevent investigating blackbox models with blackbox interpretability techniques.
Requirements
Proficient with scikit-learn: pipelines, column transformers, linear models, more complex models (e.g. random forests and gradient boosting)
Clients we've helped
What you'll learn
- Understand the use cases for model explainability (debug, right to explanation, etc.)
- Understand when model explainability is not enough (e.g. causality and fairness)
- Categorize the methods covered between sensitivity/impact and global/local
- Apply the methods with the provided packages
- Explain the inner workings of all methods
- Articulate the downsides for each method
- Evaluate whether a method is appropriate for the business use case
The schedule
- Addictive Attributions
- Partial Dependence Plots
- Individual Conditional Expectation Curves
- Permutation Importance
- Shapley Values