Fiona K. Ewald
@fionaewald.bsky.social
PhD Student @ LMU Munich
Munich Center for Machine Learning (MCML)
Research in Interpretable ML / Explainable AI
Munich Center for Machine Learning (MCML)
Research in Interpretable ML / Explainable AI
Great experience presenting my work in progress on #RashomonSets for #interpretability and #performance analysis at MCML Munich AI Day last week!
A fantastic chance to connect, learn, and share ideas - big thanks to the @munichcenterml.bsky.social for organizing.
#AI #MachineLearning #IML #xAI
A fantastic chance to connect, learn, and share ideas - big thanks to the @munichcenterml.bsky.social for organizing.
#AI #MachineLearning #IML #xAI
July 7, 2025 at 5:02 PM
Great experience presenting my work in progress on #RashomonSets for #interpretability and #performance analysis at MCML Munich AI Day last week!
A fantastic chance to connect, learn, and share ideas - big thanks to the @munichcenterml.bsky.social for organizing.
#AI #MachineLearning #IML #xAI
A fantastic chance to connect, learn, and share ideas - big thanks to the @munichcenterml.bsky.social for organizing.
#AI #MachineLearning #IML #xAI
Thank you so much @daiichisankyo.bsky.social for welcoming me in your office in Munich!
Great visit to Daiichi Sankyo in Munich! Thanks to Felix Just & Roger Garriga for the warm welcome. We shared exciting work from Simon Schallmoser, Shanshan Bai & Fiona Ewald on treatment effects, synthetic datasets & feature importance. Looking forward to more collabs! #MCML
May 24, 2025 at 5:56 PM
Thank you so much @daiichisankyo.bsky.social for welcoming me in your office in Munich!
Reposted by Fiona K. Ewald
Feature importance measures can clarify or mislead. PFI, LOCO, and SAGE each answer a different question.
Understand how to pick the right tool and avoid spurious conclusions: mcml.ai/news/2025-03...
@fionaewald.bsky.social @ludwig-bothmann.bsky.social @giuseppe88.bsky.social @gunnark.bsky.social
Understand how to pick the right tool and avoid spurious conclusions: mcml.ai/news/2025-03...
@fionaewald.bsky.social @ludwig-bothmann.bsky.social @giuseppe88.bsky.social @gunnark.bsky.social
mcml.ai
May 12, 2025 at 12:54 PM
Feature importance measures can clarify or mislead. PFI, LOCO, and SAGE each answer a different question.
Understand how to pick the right tool and avoid spurious conclusions: mcml.ai/news/2025-03...
@fionaewald.bsky.social @ludwig-bothmann.bsky.social @giuseppe88.bsky.social @gunnark.bsky.social
Understand how to pick the right tool and avoid spurious conclusions: mcml.ai/news/2025-03...
@fionaewald.bsky.social @ludwig-bothmann.bsky.social @giuseppe88.bsky.social @gunnark.bsky.social
The @munichcenterml.bsky.social recently shared our work: mcml.ai/news/2025-03... 🙏🏻
#mcml #ai #interpretability #iml #xAI #blockpost
#mcml #ai #interpretability #iml #xAI #blockpost
Beyond the Black Box: Choosing the Right Feature Importance Method
The team of Bernd Bischl created a clear guide to feature importance methods, helping researchers and practitioners interpret AI models effectively.
mcml.ai
March 28, 2025 at 1:24 PM
The @munichcenterml.bsky.social recently shared our work: mcml.ai/news/2025-03... 🙏🏻
#mcml #ai #interpretability #iml #xAI #blockpost
#mcml #ai #interpretability #iml #xAI #blockpost
Need an implementation of a conditional sampler, as required, e.g., in Conditional Feature Importance, for a project in R. Since I don't think it's efficient for everyone to implement their own, I'll ask around: Do you know a good implementation?
December 1, 2024 at 8:39 AM
Need an implementation of a conditional sampler, as required, e.g., in Conditional Feature Importance, for a project in R. Since I don't think it's efficient for everyone to implement their own, I'll ask around: Do you know a good implementation?
Reposted by Fiona K. Ewald
What makes AI research excellent?
Who are the researchers behind MCML?
And what drives us at MCML?
Get to know us in our image film ⬇
Who are the researchers behind MCML?
And what drives us at MCML?
Get to know us in our image film ⬇
MCML Imagefilm
YouTube video by MCML_Munich Center for Machine Learning
www.youtube.com
November 26, 2024 at 4:09 PM
What makes AI research excellent?
Who are the researchers behind MCML?
And what drives us at MCML?
Get to know us in our image film ⬇
Who are the researchers behind MCML?
And what drives us at MCML?
Get to know us in our image film ⬇
Excited to be part of this platform!
My research focuses on global model-agnostic feature importance. Please check our recent paper: "A Guide to Feature Importance Methods for Scientific Inference" (link.springer.com/chapter/10.1...).
My research focuses on global model-agnostic feature importance. Please check our recent paper: "A Guide to Feature Importance Methods for Scientific Inference" (link.springer.com/chapter/10.1...).
A Guide to Feature Importance Methods for Scientific Inference
While machine learning (ML) models are increasingly used due to their high predictive power, their use in understanding the data-generating process (DGP) is limited. Understanding the DGP requires ins...
link.springer.com
November 24, 2024 at 10:49 AM
Excited to be part of this platform!
My research focuses on global model-agnostic feature importance. Please check our recent paper: "A Guide to Feature Importance Methods for Scientific Inference" (link.springer.com/chapter/10.1...).
My research focuses on global model-agnostic feature importance. Please check our recent paper: "A Guide to Feature Importance Methods for Scientific Inference" (link.springer.com/chapter/10.1...).