General Information
SSD: ING-INF/05
CFU: 6
Lecturer: Eliana Pastor
Teaching Staff: Gabriele Ciravegna, Eleonora Poeta
⏰ Schedule
- Thursday, 16:00-19:00 – classroom 14
- 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)
- Post-hoc (model agnostic) – local – gradient-based explanation methods (slides)
- Evaluation of explanations (slides)
- Concept-based Explainable AI – Part I (slides), Part II (slides)
- Introduction to NLP (pdf)
- Counterfactual explanations (slides)
- Attention-based Explainability (slides)
- Mechanistic Interpretability (slides)
💻 Laboratory Material
- Lab 0 – ML Pipeline Review: Scikit-learn & PyTorch (zip)
- Lab 1 – Interpretable by Design Models (zip) (solution) (pdf_solution)
- Lab 2 – Post-hoc global explanation methods (zip) (solution) (pdf_solution)
- Lab 3a – Post-hoc local explanation methods – LIME (zip)
- Lab 3B – Post-hoc local explanation methods – SHAP (zip) (solution) (pdf_solution)
- Lab 4 – XAI for Image data (zip)(solution)
- Lab 5 – Concept-based XAI (zip)
- Lab 6a – NLP Classifier Training with HuggingFace (zip)
- Lab 6b – Explainable NLP (zip) (solution) (predicted_labels)
- Lab 7a, 7b: Evaluating Explanations (zip_a, zip_b)
- Lab 8: Counterfactual explanations (zip)
Project
- Link form for the group and project indication, deadline 4/05/2026
- In the case you have problems in creating a group, register individually, specifying your project preferences and constraints (e.g., expected project submission) in the comment section
- Project teams (pdf)
- Contact eliana.pastor@polito.it for any issues (e.g., late project indication, missing team)
- List projects (pdf)
- Presentation projects (pdf)