MSCA Digital: The Need for Explainable AI

This course is part of the MSCA Digital Training Week and provides a structured introduction to explainable AI (xAI).

0 Rating
0 Reviews
6 Students Enrolled

Wishlist

Free

Enroll Now

Tags:

Course Content

6 courselets

	White Box Models (pdf)	3.2 M

	SHAP and Lime Deep Dive (pdf)	1.77 M

	Deep Learning xAI (pdf)	2.74 M

	Time-Series based xAI Methods (pdf)	3.76 M

	Tutorial on Explainable Reinforcement Learning (XRL) (pdf)	536.53 K

Requirements

1) Foundations in Machine Learning – understanding of supervised learning, model training, overfitting, feature importance. 2) Mathematical Background – basic linear algebra, probability, and statistics (enough to follow Shapley values and regression concepts). 3) Programming Skills – ability to work with Python (libraries such as scikit-learn, XGBoost, SHAP, LIME).

General Overview

Description

As part of the MSCA Digital Training Week, this course offers a comprehensive journey through the foundations and frontiers of explainable AI (xAI). Participants will begin with interpretable “white box” models before advancing to widely used explainability methods such as feature importance, partial dependence plots (PDP), individual conditional expectation (ICE), SHAP, and LIME. The program combines conceptual learning with hands-on sessions, including a practical demonstration of applying xAI in public employment services.

Building on these foundations, the course explores explainability in complex machine learning architectures, focusing on deep learning and time-series forecasting models.

By the end of the course, participants will have gained both theoretical knowledge and practical skills to apply, evaluate, and reflect on xAI methods across a variety of data types and applications.