Explainable AI for the Sciences: Towards Novel Insights - IPAM

Explainable AI for the Sciences: Towards Novel Insights

Part of the Workshop Explainable AI for the Sciences: Towards Novel Insights
January 9 - 13, 2023

Schedule

All times in this Schedule are Pacific Time (PT)

Monday, January 9, 2023

Morning Session

08:00-08:55
Check-In/Breakfast (Hosted by IPAM)
08:55-09:00
Welcome & Opening Remarks: Dean Miguel García-Garibay (Dean of Physical Sciences, UCLA) and Dima Shlyakhtenko (Director, IPAM)
09:00-09:00
Session Chair: Tulay Adali
09:00-09:50
Bolei Zhou (University of California, Los Angeles (UCLA))
From Network Dissection to Policy Dissection: Discovering Emergent Concepts in Deep Representations
10:00-10:15
Break
10:15-11:05
Klaus-Robert Müller (Technische Universität Berlin)
Virtual Talk:
11:15-11:30
Break
11:30-12:20
Xiao Fu (Oregon State University)
Understanding Multiview and Self-Supervised Representation Learning: A Nonlinear Mixture Identification Perspective

Afternoon Session

12:30-14:30
Lunch (on your own)
14:30-15:20
Jaesik Choi (Korea Advanced Institute of Science and Technology (KAIST))
Explainable Artificial Intelligence to Analyze Internal Decision Mechanism of Deep Neural Networks
15:30-15:50
Break
15:50-16:40
Bin Yu (University of California, Berkeley (UC Berkeley))
Virtual Talk: Interpreting Deep Neural Networks towards Trustworthiness
16:45-17:20
Lightning Poster Session
17:20-18:30
Poster Session & Reception (Hosted by IPAM)

Tuesday, January 10, 2023

Morning Session

08:00-09:00
Check-In/Breakfast (Hosted by IPAM)
09:00-09:00
SESSION CHAIR: Michele Ceriotti
09:00-09:50
Osbert Bastani (University of Pennsylvania)
Interpretable Machine Learning via Program Synthesis
10:00-10:15
Break
10:15-11:05
Wojciech Samek (Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute, HHI)
Virtual Talk: Concept-Level Explainable AI
11:15-11:30
Break
11:30-12:20
Tülay Adali (University of Maryland Baltimore County)
Matrix and Tensor Factorizations for Data Fusion: Focus on Model Match, Interpretability, and Reproducibility

Afternoon Session

12:30-14:30
Lunch (on your own)
14:30-15:20
Frederick Klauschen (Ludwig-Maximilians-Universität München)
AI in cancer research and diagnostics

Wednesday, January 11, 2023

Morning Session

08:00-09:00
Check-In/Breakfast (Hosted by IPAM)
09:00-09:00
SESSION CHAIR: Pamela Douglas
09:00-09:50
Evrim Acar (Simula Research Laboratory)
Virtual Talk: Extracting Insights from Complex Data: Constrained Multimodal Data Mining using Coupled Matrix and Tensor Factorizations
10:00-10:15
Break
10:15-11:05
Michele Ceriotti (MLPRC2)
Physical insights from atomic-scale machine learning
11:15-11:30
Break
11:30-12:20
Cecilia Clementi (Freie Universität Berlin)
Efficient algorithms for Non-Local Filtering and applications to Cryo-Electron microscopy and biological microscopy

Afternoon Session

12:30-14:30
Lunch (on your own)
14:30-15:20
Petros Koumoutsakos (Harvard University)
Alloys of Artificial Intelligence and Scientific Computing for Fluid Mechanics
15:30-15:50
Break
15:50-16:40
Gregoire Montavon (Freie Universität Berlin)
Virtual Talk: Towards Higher-Order and Disentangled Explainable AI

Thursday, January 12, 2023

Morning Session

08:00-09:00
Check-In/Breakfast (Hosted by IPAM)
09:00-09:50
André Freitas (University of Manchester)
Building explanation machines for science: a neuro-symbolic perspective
10:00-10:15
Break
10:15-11:05
Matteo Valleriani (Technische Universität Berlin)
XAI Historian
11:15-11:30
Break
11:30-12:20
Oliver Eberle (Technische Universität Berlin)
Explainable structured machine learning in similarity, graph and transformer models.

Afternoon Session

12:30-14:30
Lunch (on your own)
14:30-15:20
Anders Søgaard (University of Copenhagen)
What’s Opaque to Whom - and Why?
15:30-15:50
Break
15:50-16:40
Panel Discussion

Friday, January 13, 2023

Morning Session

08:00-09:00
Check-In/Breakfast (Hosted by IPAM)
09:00-09:50
Vince Calhoun (Georgia Institute of Technology)
Title not available
10:00-10:15
Break
10:15-11:05
Pamela Douglas (UCLA Medical School)
Title not available
11:15-11:30
Break
11:30-12:20
Nikolaus Kriegeskorte (Columbia University)
Controversial stimuli: Optimizing experiments to adjudicate among computational hypotheses

Afternoon Session

12:30-14:30
Lunch (on your own)
14:30-15:20
Lisa Nickerson (Harvard Medical School)
Addressing Confounds in Neuroimaging Machine Learning Predictions
Printable Version