While Model Trains

Read data blog posts.
Carefully handpicked.
Presented 3 at a time.

Minimizing the Negative Log-Likelihood, in English

Will Wolf

"Why are you calling it the negative log-likelihood?"

Read it!

Writing Robust Tests for Data & Machine Learning Pipelines

Eugene Yan

An in-depth analysis of why certain types of tests break more frequently than others, along with suggestions for creating more robust pipeline tests.

Read it!

Are Pop Lyrics Getting More Repetitive?

Colin Morris

A fascinating visual essay that utilizes the Lempel-Ziv algorithm (which powers GIFs, PNGs, and most archive formats) to analyze if pop songs are becoming more repetitive.

Read it!