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.
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
- Addictive Attributions
- Partial Dependence Plots
- Individual Conditional Expectation Curves
- Permutation Importance
- Shapley Values
Data Science Learning Journey
Rens DimmendaalData Scientist
Structured, to-the-point, good combination of theory and practical examples, very knowledgeable trainer who can explain concepts very well
It was a hands-on and tangible course. We could apply what we learned in a matter of minutes. The trainer did a great job of answering ad-hoc questions that complemented the material. We appreciated the fact that we could apply what we were taught directly to our company.
I liked every aspect of this training and would like to thank the trainers. They did an excellent job of explaining how to use Spark for data science. This is the fourth GoDataDriven training I’ve followed. All were great, but this was the best one so far.
Climbing a steep Python and Machine Learning curve in three days. This would have taken me months on my own.