OpenAI right now

The original SHAP paper has been cited over 30k times.

The paper showed that attribution methods, like LIME and LRP, compute Shapley values (with some adaptations).

The paper also introduces estimation methods for Shapley values, like KernelSHAP, which today is deprecated.

How I sometimes feel working on "traditional" machine learning topics instead of generative AI stuff 😂

Looking for a Christmas gift for a stubborn Bayesian or an over-hyped AI enthusiast?

Modeling Mindsets is a short read to broaden your perspective on data modeling.

christophmolnar.com/books/modeli...

*Hat not included.

Without non-linear activation functions, neural networks would be linear models, no matter how many layers are stacked.

Got myself a Samsung Galaxy S9 tablet for note-taking, and I love it.

(and yes, I'm reading my own book here as a reference for another project, feeling like an imposter because I don't have everything memorized 😂)

I'm always amazed at how popular the random forest algorithm is for remote sensing research. I would have expected deep learning to be more popular there (not to say it isn't).

Must be an attraction to trees. 😁

What's the difference between explainability and interpretability? Does the machine learning community have an agreed-upon definition?

No.

There's a great overview, which is from this paper: arxiv.org/abs/2211.08943

My take: I prefer interpretability since the term explainability is too strong.

Machine learning and statistics have very narrow ideas of what a model is and how to abstract the world.

To broaden the "model" horizon, I can recommend these two books:

• Thinking in Systems by Donella H. Meadows
• Simulation and Similarity by Michael Weisberg

(ignore the monkey)

Just realized BlueSky allows sharing valuable stuff cause it doesn't punish links. 🤩

Let's start with "What are embeddings" by @vickiboykis.com

The book is a great summary of embeddings, from history to modern approaches.

The best part: it's free.

Link: vickiboykis.com/what_are_emb...

That's a Quarto feature. At least you define it in the Quarto config file (_quarto.yml), see screenshot. Not always sure where Quarto ends and pandoc begins

Even as an interpretable ML researcher, I wasn't sure what to make of Mechanistic Interpretability, which seemed to come out of nowhere not too long ago.

But then I found the paper "Mechanistic?" by
@nsaphra.bsky.social and @sarah-nlp.bsky.social, which clarified things.

After years of writing with Vim, it's finally time to write my books in a modern editor.

Time to enter the 21st century of editors.

A new era of writing. A new me.

I love random forests

That's such a simple yet great idea for a reference book for any machine learning person.

The first pages look very promising, I love the visuals for the metrics:

Interested in machine learning in science?

Timo and I recently published a book, and even if you are not a scientist, you'll find useful overviews of topics like causality and robustness.

The best part is that you can read it for free: ml-science-book.com

Working on the 3rd edition of Interpretable Machine Learning.

My first approach was to just add a few chapters, update some sections.

As I go deeper, I realize I go fully into "rewrite" mode.

Had to add a reminder not to rewrite the entire book 😂