Lilian Weng • 8/1/2017

How to Explain the Prediction of a Machine Learning Model?

This article discusses the critical need for explainability in machine learning models, particularly in high-stakes domains like finance, healthcare, and criminal justice. It introduces key concepts of model interpretability, such as simulatability and decomposability, and begins a technical review of interpretable models, starting with linear regression and coefficient analysis.

0 comments

#Machine Learning #Deep Learning #Ethics