====== Explainable Artificial Intelligence ======
  * Course ID: WFAIS.IF-XG325.0
  * Room: G-1-08
  * Teachers:
    * Lectures: [[https://szymon.bobek.re|dr inż. Szymon Bobek]] (SBK)
    * Labs: 
      * Mondays [[https://szymon.bobek.re|dr inż. Szymon Bobek]] (SBK)
      * Wednesdays [[https://www.linkedin.com/in/manai-sabri|Sabri Manai, PhD Candidate]] (SMI)

====== Lectures ======
  * **[07.10.2025]** [SBK] Lecture plan, rules, organizaiton of classes
  * **[13.10.2025]** [SBK] {{ :courses:xai:1_introduction_to_explainable_artificial_intelligence_2024.pdf |Introduction to xAI}}
  * **[20.10.2025]** [SBK] {{ :courses:xai:2_inherently_interpretable_models.pdf |Inherently interpretable models I}}
  * **[27.10.2025]** [SBK] {{ :courses:xai:3_inherently_interpretable_models.pdf |Inherently interpretable models II}}
  * **[03.11.2025]** [SBK] {{ :courses:xai:4_surrogate_models.pdf |Global model-agnostic explanations and surrogate models}}
  * **[17.11.2025]** [SBK] {{ :courses:xai:5_local_model-agnostic_explanations.pdf |Local model-agnostic explanations I}}
  * **[24.11.2025]** [SBK] {{ :courses:xai:6_local_model-agnostic_explanations.pdf |Local model-agnostic explanations II}}
  * **[01.12.2025]** [SBK] Hands-on programming assignments
  * **[08.12.2025]** [SBK] {{ :courses:xai:7_conterfactual_and_adversarial_explanations.pdf |Counterfactual explanations}}
  * **[15.12.2025]** [SBK] {{ :courses:xai:8_evaluation_methods.pdf |Evaluation of XAI algorithms}}
  * **[12.01.2025]** [SBK] {{ :courses:xai:9_explainability_in_neural_networks.pdf |Explanations in Neural Networks}}
  * **[19.01.2026]** [SBK] {{ :courses:xai:10_industrial_challenges_for_xai.pdf |Challenges of XAI in Industrial applications}}
  * **[26.01.2026]** [SBK] Hands-on programming assignments
  * **[:?:]** :!: **Exam: TBD** :!:
  * **[:?:]** :!: **Exam 2nd term: TBD** :!:

  * **Lectures Videos**: [[https://ujchmura-my.sharepoint.com/:f:/g/personal/szymon_bobek_uj_edu_pl/Erm88RcLMYhAmCLLmRitz-QBKTKZydDWoYF0j6YqKsSY0g?e=dU3uSM|Watch here]]
====== Labs (Mondays 10:00, G-1-08)======
  * **[13.10.2025]** [SBK] [[.:lab1|Introduction to working environment, basics of data manipulation and visualization and bias identification]]
  * **[20.10.2025]** [SBK] [[.:lab2|Inherently interpretable models]]
  * **[27.10.2025]** [SBK] [[.:lab3|Inherently interpretable models II]]
  * **[03.11.2025]** [SBK] [[.:lab4|Global model-agnostic approaches I]]
  * **[17.11.2025]** [SBK] [[.:lab5|Local model-agnostic approaches I]]
  * **[24.11.2025]** [SBK] [[.:lab6|Local model-agnostic approaches II]]
  * **[01.12.2025]** Test I
  * **[01.12.2025]** [SBK] [[.:p1_2024|Programming Assignment I]]
  * **[08.12.2025]** [SBK] [[.:lab7|Counterfactual explanations]]
  * **[15.12.2025]** [MTM] [[.:lab8|Evaluation of XAI methods]]
  * **[12.01.2026]** [BMK] [[.:lab9|Explainability in DNN]]
  * **[19.01.2026]** [SBK] [[.:p2_2024|Programming Assignment II]]
  * **[26.01.2025]** Test II
  * **[26.01.2025]** [SBK] Projects presentations/discussion

====== Labs (Wednesdays 18:30, G-1-03)======
  * **[15.10.2025]** [SMI] [[.:lab1|Introduction to working environment, basics of data manipulation and visualization and bias identification]]
  * **[22.10.2025]** [SMI] [[.:lab2|Inherently interpretable models]]
  * **[29.10.2025]** [SMI] [[.:lab3|Inherently interpretable models II]]
  * **[05.11.2025]** [SMI] [[.:lab4|Global model-agnostic approaches I]]
  * **[12.11.2025]** [SMI] [[.:lab5|Local model-agnostic approaches I]]
  * **[19.11.2025]** [SMI] [[.:lab6|Local model-agnostic approaches II]]
  * **[26.11.2025]** Test I
  * **[26.11.2025]** [SMI] [[.:p1_2024|Programming Assignment I]]
  * **[03.12.2025]** [SMI] [[.:lab7|Counterfactual explanations]]
  * **[10.12.2025]** [SMI] [[.:lab8|Evaluation of XAI methods]]
  * **[17.12.2025]** [SMI] [[.:lab9|Explainability in DNN]]
  * **[14.01.2026]** [SMI] [[.:p2_2024|Programming Assignment II]]
  * **[21.01.2026]** Test II
  * **[21.01.2026]** [SMI] Projects presentations/discussion
====== Grading rules ======
  * 100 EXP is 100% of the total points (MAX) from the lab. This consists of:
    * 2x25 EXP - two tests, covering material from the laboratories and lecture
    * 2x25 EXP - two assignments carried out in groups (2-5 people) during the laboratory

  * The above result may be increased by any "pluses" for activity during classes (1 plus = 1 EXP) and extra programming assignments rated  individually (3-5 EXP)
    * Advantages are taken into account only when passing the exam within the basic deadline.
  * All laboratory projects must be submitted on time.
    * The mark for late projects will be multiplied by 0.5 (i.e. a maximum of half the number of points can be obtained for a late project).
    * You must obtain at least 60% of points in all tests.
    * Two unexcused absences are allowed.
    * Each subsequent absence results in a deduction of 10 EXP.
===== Grading scale: =====

  * >= 90 EXP – bdb
  * >= 80 EXP – db+
  * >= 70 EXP – db
  * >= 60 EXP – dst+
  * >= 50 EXP – dst
  * < 50 EXP – ndst
====== References ======
  * [[https://christophm.github.io/interpretable-ml-book/|Interpretable Machine Learning]]