Explainable and trustworthy AI (2024/2025)

Explainable and trustworthy AI (2024/2025)

General Information

SSD: ING-INF/05

CFU: 6

Lecturer: Eliana Pastor

Teaching Staff: Gabriele Ciravegna, Eleonora Poeta

Information:

Dear Students,

Please note that due to an institutional event, there will be no lecture tomorrow, March 17.

Schedule

  • Monday, 8:30-10:00 – classroom 11T
  • Thursday, 8:30-10:00 – classroom 5T
  • Friday, 8:30-10:00 –  classroom 2I

Teaching material

  • Course introduction (slides)
  • Trustworthy AI: definition and motivations (slides)
  • Explainable AI: taxonomy (slides)
  • Pre-modeling explainability (slides)
  • In-modeling explainability (slides)
  • Post-hoc model agnostic – global (slides)
  • Post-hoc model agnostic – local surrogate models (slides)
  • Post-hoc model agnostic – local – explaining by removing/perturbing (slides) [UPDATED]
  • Post-hoc (model agnostic) – local – gradient-based explanation methods (slides)
  • Concept-based Explainable AI – part I (slides)
  • Concept-based Explainable AI – part II (slides)
  • Introduction to NLP (slides)
  • Evaluation of explanations (slides – 2024)
  • Adversarial Attacks (slides – 2024)
  • Attention-based Explainability (slides – 2024)
  • Counterfactual explanations (slides – 2024)

Laboratory material

Project

  • Extended deadline for form submission: May 14, 23:59 AOE
  • List projects (pdf)
  • Presentation projects (pdf)
  • Template project Latex (link)
  • We suggest using Overleaf