Prof. Kowalski Leads Course on Explainable AI in Neural Networks
Modena
From November 7th to 14th, Prof. Piotr Andrzej Kowalski will be teaching an advanced course on Explainable Artificial Intelligence (XAI) with a focus on neural networks. The course, aimed at shedding light on the decision-making processes of complex neural models, addresses one of AI's biggest challenges: its "black-box" nature.
Throughout the five sessions, participants will learn essential interpretability techniques such as LIME and SHAP, explore sensitivity analysis methods, and delve into real-world applications in healthcare and environmental monitoring. A strong emphasis will also be placed on ethical issues, including bias and fairness in AI.