Birs- 22w5055: Interpretability in Artificial Intelligence

  1. Title:
    Friends Don’t Let Friends Deploy Black-Box Models: The Importance of Intelligibility in Machine Learning

    Speaker:

    Link:

  2. Title:
    Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations

    Speaker:

    Link:

  3. Title:
    Quantitative assessment of attention based explanations

    Speaker:

    Link:

  4. Title:
    Through the Looking-Glass: Understanding Model Behavior

    Speaker:

    Link:

  5. Title:
    Flash Talk: Interpretability needs for ML in GWAS and intensive care

    Speaker:

    Link:

  6. Title:
    Focus! Rating XAI Methods and Finding Biases

    Speaker:

    Link:

  7. Title:
    The AGI is here. The Artificial General Idiot, that is. Human General Intelligence to the rescue!

    Speaker:

    Link:

  8. Title:
    Interpretable Machine Learning for Safety and Teaming

    Speaker:

    Link:

  9. Title:
    Fully differentiable rule learning

    Speaker:

    Link:

  10. Title:
    Fast Sparse Decision Tree Optimization

    Speaker:

    Link:

  11. Title:
    Concept Whitening for Interpretable Image Recognition

    Speaker:

    Link:

  12. Title:
    The Extreme of Interpretability in Machine Learning: Sparse Generalized Additive Models and Optimal Sparse Decision Trees

    Speaker:

    Link:

  13. Title:
    Panel Discussion "Biases in AI"

    Speaker:

    Link:

  14. Title:
    Discovering hidden signatures in biomedical data across space and time

    Speaker:

    Link:

  15. Title:
    Causal Perspectives in Explaining Neural Network Models

    Speaker:

    Link:

  16. Title:
    Interpretability in Artificial Intelligence applications for rare diseases

    Speaker:

    Link:

  17. Title:
    Interpretable models in genomics

    Speaker:

    Link:

  18. Title:
    Building a Mind for Cancer

    Speaker:

    Link:

  19. Title:
    Learning biology from the data with interpretable machine learning

    Speaker:

    Link:

  20. Title:
    Evidence-Driven Learning for Interpretability

    Speaker:

    Link: