https://mindfulmodeler.substack.com/p/what-are-shapley-interactions-and What Are Shapley Interactions, and Why Should You Care?Christoph MolnarDec 03, 2024 “Shapley values are the go-to method for explainable AI because they are easy to interpret and theoretically
What I Read: ML, Go
https://eli.thegreenplace.net/2024/gomlx-ml-in-go-without-python/#footnote-reference-2 GoMLX: ML in Go without PythonEli BenderskyNovember 22, 2024 at 07:00 “GoMLX is a relatively new Go package for ML that deserves some attention.”
What I Read: data engineering
https://javisantana.com/2024/11/30/learnings-after-4-years-data-eng.html Learnings after 4 years working with +50 companies on data engineering projectsJavi Santana “I like to call it “high performance data engineering”…. Some practical learnings, in no particular order…”
What I Read: Autoencoders, Interpretability
https://adamkarvonen.github.io/machine_learning/2024/06/11/sae-intuitions.html An Intuitive Explanation of Sparse Autoencoders for LLM InterpretabilityAdam KarvonenJun 11, 2024 “Sparse Autoencoders (SAEs) have recently become popular for interpretability of machine learning models…”