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)
- Attention-based Explainability (slides)
- Mechanistic Interpretability (slides)
- Adversarial Attacks (slides)
- Counterfactual explanations (slides)
Laboratory material
- Lab 0.1: Machine Learning pipeline with Pandas and Scikit-learn (zip) (zip_solution) (pdf_solution)
- Lab 0.2: Introduction to Deep Learning with PyTorch (zip) (zip_solution) (pdf_solution)
- Lab 1: Interpretable by-design (zip) (zip_solution) (pdf_solution)
- Lab 2: Post-hoc global explanation methods (zip) (zip_solution) (pdf_solution)
- Lab 3a: Post-hoc Local explanation methods – LIME (zip) (zip_solution) (pdf_solution)
- Lab 3b: Post-hoc Local explanation methods – SHAP (zip) (zip_solution) (pdf_solution)
- Lab 4a: Image Data Analsys & Saliency Map (zip) (zip_solution) (pdf_solution)
- Lab 4b: XAI for Image Data (zip) (zip_solution) (pdf_solution)
- Lab 5: Concept-based Explainable AI (zip) (zip_solution)
- Lab 6a: NLP Classifier Training with HuggingFace (zip) (data_zip)
- Lab 6b: Explainable NLP (zip) (zip solution) (data_zip)
- Lab 7a, 7b: Evaluating Explanations (zip_a, zip_b) (zip solution)
- Lab 8: Attention-based Explainable AI (zip) (zip_solution)
- Lab 9: Adversarial Attacks and Defenses (zip)
- Lab 10: Counterfactual explanations (zip)
Calendar
| Date | Topic |
| 22/05/2025 8:30-10:00 | Lecture: Model robustness – adversarial attacks |
| 23/05/2025 8:30-10:00 | Lab 9: Adversarial attack & Project tutoring XAI Seminar: Alan Perotti (CENTAI) |
| 26/05/2025 8:30-10:00 | Lecture: Explanation by example – counterfactual |
| 26/05/2025 10:00-11:30 | XAI Seminar: José Oramas (University of Antwerp) Project tutoring |
| 29/05/2025 8:30-10:00 | Lab 10: Counterfactual explanations |
| 30/05/2025 8:30-10:00 | Project tutoring XAI Seminar: Riccardo Renzulli (UniTO) |
| 05/06/2025 8:30-10:00 | Exam Example |
| 06/06/2025 8:30-10:00 | Project tutoring |