Arvutiteaduse instituut
  1. Kursused
  2. 2022/23 sügis
  3. Arvutusliku neuroteaduse seminar (MTAT.03.292)
EN
Logi sisse

Arvutusliku neuroteaduse seminar 2022/23 sügis

  • Main
  • Process
  • Timetable
  • Tips

Timetable

You can book when to present from this sheet. You can book a time even if you didn't select or found a paper yet. The earlier you book the better you can manage your schedule.

06.09 Week 0: Kick-off seminar
Introduction, organization of the seminar, questions.
slides | recording


13.09 Week 1: Explanation in artificial intelligence: Insights from the social sciences.
presented by Maksym Del
feedback | test | recording

20.09 Week 2: A survey on explainable artificial intelligence (xai): Toward medical xai
presented by Giacomo Magnifico
slides | feedback | test | recording

27.09 Week 3: Does the chimpanzee have a theory of mind?.
presented by Nicholas Sujecki
feedback | test | slides | recording

04.10 Week 4: Machine theory of mind. In International conference on machine learning
presented by Ondrej Sevcik
feedback | test | recording

11.10 Week 5: No presentation


18.10 Week 6: CX-ToM: Counterfactual explanations with theory-of-mind for enhancing human trust in image recognition models.
presented by Ekaterina Sedykh
feedback | test | recording

25.10 Week 7: Metrics for Explainable AI: Challenges and Prospects
presented by Roman Karpenko
feedback | test | recording

01.11 Week 8: Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanations
presented by Braian O. Dias
feedback | test | slides | recording

08.11 Week 9: Introduction to SHAP and Counterfactual Shapley Additive Explanations.
presented by Marharyta Domnich
slides | colab notebook 1 | colab notebook 2 | recording
feedback | test

15.11 Week 10: What does LIME really see in images?
presented by Tõnis Hendrik Hlebnikov
feedback | test | slides | recording

22.11 Week 12: Fairness Through Robustness: Investigating Robustness Disparity in Deep Learning.
presented by Chan Wai Tik
feedback | test | recording

29.11 Week 13: book - A multidimensional conception and measure of human-robot trust. Trust in Human-Robot Interaction
presented by Carolin Lüübek
paper - What Does it Mean to Trust a Robot. Steps Toward a Multidimensional Measure of Trust
feedback | test | recording


06.12 Week 14: What is Human-like?: Decomposing Robots’ Human-like Appearance Using the Anthropomorphic roBOT (ABOT) Database
presented by Hain Zuppur
feedback | test


Extra papers:

  1. Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods.
  2. OptiLIME: Optimized LIME Explanations for Diagnostic Computer Algorithms.
  3. "Why Should You Trust My Explanation?" Understanding Uncertainty in LIME Explanations, 2019
  4. Reliable Post hoc Explanations: Modeling Uncertainty in Explainability
  5. A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle.
  6. Contrastive explanation: a structural-model approach.
  7. On the role of knowledge graphs in explainable AI.
  8. Improving Model Understanding and Trust with Counterfactual Explanations of Model Confidence.
  9. One Explanation is Not Enough: Structured Attention Graphs for Image Classification.
  10. Axiomatic Attribution for Deep Networks. - Integrated Gragients founding paper
  11. Grad-CAM: Visual Explanations From Deep Networks via Gradient-Based Localization.
  12. Grad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks.
  13. XAI tutorials: https://github.com/flecue/xai-aaai2022
  • Arvutiteaduse instituut
  • Loodus- ja täppisteaduste valdkond
  • Tartu Ülikool
Tehniliste probleemide või küsimuste korral kirjuta:

Kursuse sisu ja korralduslike küsimustega pöörduge kursuse korraldajate poole.
Õppematerjalide varalised autoriõigused kuuluvad Tartu Ülikoolile. Õppematerjalide kasutamine on lubatud autoriõiguse seaduses ettenähtud teose vaba kasutamise eesmärkidel ja tingimustel. Õppematerjalide kasutamisel on kasutaja kohustatud viitama õppematerjalide autorile.
Õppematerjalide kasutamine muudel eesmärkidel on lubatud ainult Tartu Ülikooli eelneval kirjalikul nõusolekul.
Tartu Ülikooli arvutiteaduse instituudi kursuste läbiviimist toetavad järgmised programmid:
euroopa sotsiaalfondi logo