Mindful Modeler

Home
Archive
About
New
Top
Discussion
Use interpretability to improve and debug your ML model
How I used feature importance to fix my model
 • 
Christoph Molnar
November 2023
Don't be dogmatic about interpretability-by-design versus post-hoc
When to use which ML interpretation approach
 • 
Christoph Molnar
4
But have you considered writing your own evaluation metric?
The Strategic Use of Custom Metrics in Machine Learning
 • 
Christoph Molnar
4
Bridging the Gap: From Statistical Distributions to Machine Learning Loss Functions
When I consulted researchers on which statistical analysis to use for their data, a common first step was to think about the distribution of the target…
 • 
Christoph Molnar
5
A Grandmaster's Guide to Machine Learning Challenges
Picking the Right Challenges and Succeeding
 • 
Christoph Molnar
3
October 2023
Should we stop interpreting ML models because XAI methods are imperfect?
The Case for Imperfect Interpretability
 • 
Christoph Molnar
The Intricate Link Between Compression and Prediction
How Gzip and K-Nearest Neighbors Can Outperform Deep Learning Models
 • 
Christoph Molnar
3
Machine learning eats up science
A new era of science without understanding?
 • 
Christoph Molnar
1
What A Horse Can Tell Us About Machine Learning
How to find out whether your model relies on spurious correlations
 • 
Christoph Molnar
1
The Case for Uninterpretable Machine Learning
Machine learning excels because it's not interpretable. Not in spite of it. Interpretability is a constraint.Thanks for reading Mindful Modeler…
 • 
Christoph Molnar
7
September 2023
Machine learning interpretability from first principles
Understand interpretation methods via functional decomposition
 • 
Christoph Molnar
6
Imbalanced data? Why "Do Nothing" should be the default
And when “Do Something” is better.”
 • 
Christoph Molnar
1
© 2023 Christoph Molnar
Privacy ∙ Terms ∙ Collection notice
Start WritingGet the app
Substack is the home for great writing