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!

A few reasons to be skeptical of machine learning

Julia Evans

"why, even though machine learning is really awesome and cool and you can do super powerful and interesting things with it – why you should still be skeptical"

Read it!

Neurally Embedded Emojis

Will Wolf

This is what happens when emojis encounter neural networks.

Read it!