Fiona K. Ewald

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

07.07.2025 17:02 — 👍 2    🔁 0    💬 0    📌 0

Thank you so much @daiichisankyo.bsky.social for welcoming me in your office in Munich!

24.05.2025 17:56 — 👍 1    🔁 0    💬 0    📌 0

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

12.05.2025 12:54 — 👍 7    🔁 5    💬 0    📌 0

Thank you for sharing! 🙏🏻

28.03.2025 13:27 — 👍 0    🔁 0    💬 0    📌 0

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.

The @munichcenterml.bsky.social recently shared our work: mcml.ai/news/2025-03... 🙏🏻

#mcml #ai #interpretability #iml #xAI #blockpost

28.03.2025 13:24 — 👍 2    🔁 0    💬 0    📌 0

GitHub - bips-hb/cpi: CPI: Conditional Predictive Impact CPI: Conditional Predictive Impact. Contribute to bips-hb/cpi development by creating an account on GitHub.

I was thinking of using the implementation from the CPI package (github.com/bips-hb/cpi/) by Watson D. S. & Wright, M. N. (2021) "Testing conditional independence in supervised learning algorithms" ML.

01.12.2024 08:39 — 👍 2    🔁 0    💬 0    📌 0

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?

01.12.2024 08:39 — 👍 1    🔁 0    💬 1    📌 0

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 ⬇

26.11.2024 16:09 — 👍 9    🔁 1    💬 0    📌 0

Would be great if you could add me, too. Thank you!

26.11.2024 21:00 — 👍 1    🔁 0    💬 0    📌 0

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...

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...).

24.11.2024 10:49 — 👍 9    🔁 0    💬 0    📌 0