STA 290 Seminar: Przemek Biecek

Przemek Biecek

Event Date

Mathematical Sciences 1147 (Colloquium Room)

SPEAKER:      Przemek Biecek; Warsaw University of Technology and University of Warsaw

TITLE:             “Black-box openers: How to explain predictions from complex ML models?”

ABSTRACT:   Predictive modeling is invaded by elastic, yet complex methods such as neural networks or ensembles (model stacking, boosting or bagging). Such methods are usually described by a large number of parameters or hyper parameters - a price that one needs to pay for elasticity. The very number of parameters makes models hard to understand.

In this talk I will present and compare collection of explainers for complex predictive models, like Break Down (, LIME (, Ceteris Paribus (, Shapley Values (, auditor ( and DALEX (

Each explainer is a technique for exploration of a black box model. Presented approaches are model-agnostic, what means that they extract useful information from  any predictive method despite its internal structure.

It's a part of quickly growing area of research for XAI (Explainable Artificial Intelligence).


STA 290 Seminar List: