While Model Trains

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

In Praise of Small Data

Evan Miller

Unless you are training a model with thousands of parameters, big data should not be seen as a source of value, but rather as a source of cost.

Read it!

Building Docker Images The Proper Way

Martin Heinz

Some techniques for speeding up the build process of Docker images and make much slimmer and more secure images.

Read it!

Minimizing the Negative Log-Likelihood, in English

Will Wolf

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

Read it!