Interpretability in Artificial Intelligence
Videos from BIRS Workshop
Rich Caruana, Microsoft Research
Monday May 2, 2022 08:59 - 09:59
Friends Don’t Let Friends Deploy Black-Box Models: The Importance of Intelligibility in Machine Learning
Anna Hedstroem, TU Berlin
Monday May 2, 2022 10:29 - 11:04
Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations
Nicolas Deutschmann, IBM Research Europe
Monday May 2, 2022 11:04 - 11:35
Quantitative assessment of attention based explanations
Sara Hooker, Google Brain
Monday May 2, 2022 14:05 - 14:57
Through the Looking-Glass: Understanding Model Behavior
Juliane Klatt, ETH Zurich
Monday May 2, 2022 15:01 - 15:09
Flash Talk: Interpretability needs for ML in GWAS and intensive care
Anna Aria Duart, Barcelona Supercomputing Center
Monday May 2, 2022 15:32 - 16:01
Focus! Rating XAI Methods and Finding Biases
Dario Garcia Gasulla, Barcelona Supercomputing Center
Monday May 2, 2022 16:01 - 16:41
The AGI is here. The Artificial General Idiot, that is. Human General Intelligence to the rescue!
Kush Varshney, IBM Research
Tuesday May 3, 2022 09:00 - 09:56
Interpretable Machine Learning for Safety and Teaming
Remy Kusters, IBM Research Paris-Saclay
Tuesday May 3, 2022 10:33 - 11:06
Fully differentiable rule learning
Chudi Zhong, Duke University
Tuesday May 3, 2022 11:06 - 11:42
Fast Sparse Decision Tree Optimization
Zhi Chen, Duke University
Tuesday May 3, 2022 11:42 - 12:22
Concept Whitening for Interpretable Image Recognition
Cynthia Rudin, Duke
Tuesday May 3, 2022 14:00 - 15:00
The Extreme of Interpretability in Machine Learning: Sparse Generalized Additive Models and Optimal Sparse Decision Trees
Davide Cirillo, Barcelona Supercomputing Center (BSC)
Tuesday May 3, 2022 16:34 - 17:44
Panel Discussion "Biases in AI"
David van Dijk, Yale
Wednesday May 4, 2022 09:02 - 10:01
Discovering hidden signatures in biomedical data across space and time
Vineeth N Balasubramanian, Indian Institute of Technology
Wednesday May 4, 2022 10:33 - 11:01
Causal Perspectives in Explaining Neural Network Models
Davide Cirillo, Barcelona Supercomputing Center (BSC)
Wednesday May 4, 2022 11:14 - 11:54
Interpretability in Artificial Intelligence applications for rare diseases
Mahsa Ghanbari, Max-Delbrück-Centrer for Molecular Medicine
Wednesday May 4, 2022 11:56 - 12:26
Interpretable models in genomics
Trey Ideker, UCSD
Thursday May 5, 2022 09:03 - 10:03
Building a Mind for Cancer
Joaquin Dopazo, Fundación Progreso y Salud
Thursday May 5, 2022 10:29 - 11:05
Learning biology from the data with interpretable machine learning
Minwoo Lee, UNC Charlotte
Thursday May 5, 2022 11:06 - 11:40
Evidence-Driven Learning for Interpretability
An-phi Nguyen, ETH
Thursday May 5, 2022 11:41 - 12:21
Constrained Neural Networks for increased transparency
Guiping Hu, Rochester Institute of Technology
Thursday May 5, 2022 14:05 - 14:46
A Hybrid model to Improve Crop Yield Prediction
Marta Gonzalez Mallo, Barcelona Supercomputing Center
Thursday May 5, 2022 14:47 - 14:57
Flash Talk
Inge Wortel, Radboud University
Thursday May 5, 2022 15:30 - 15:59
Mechanistic modelling of cell migration in the immune system
Ben Lengerich, MIT
Thursday May 5, 2022 15:59 - 16:39
Sample-Specific Models for Interpretable Analysis with Applications to Disease Subtyping
Davide Cirillo, Barcelona Supercomputing Center (BSC)
Thursday May 5, 2022 16:45 - 17:48
Q&A/Brainstorming
Smita Krishnaswamy, Yale
Friday May 6, 2022 09:04 - 10:00
Deep Geometric and Topological Representations Learning for Interpretable Insights from Biomedical Data
Mara Graziani, IBM Research Zurich, Hes-so Valais
Friday May 6, 2022 10:00 - 10:40
Deep Learning Interpretability for the Discovery of Biomedical Patterns
Anshul Kundaje, Stanford University
Friday May 6, 2022 11:15 - 12:00
Interpreting deep learning models for genomic discovery