Explainable Machine Learning
![](/~ltorgo/research_lines/explainableai/featured_hub19f720a4cd6c7e7dc88cabaa24c9c3e_92681_720x0_resize_lanczos_3.png)
Methods for Helping to Understand ML Models
This research line involves studying methods for helping end-users to better understand complex and frequently black-box maching learning models. Our work is currently focused on trying to explain the reasons/conditions leading to prediction errors to serve as warnings to the use of the models for critical decisions.