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!

Why Correlation Usually ≠ Causation

Gwern

"Despite this admonition, people are overconfident in claiming correlations to support favored causal interpretations and are surprised by the results of randomized experiments, suggesting that they are biased & systematically underestimate the prevalence of confounds / common-causation."

Read it!

An intuition for Attention

Jay Mody

Developing an intuitive understanding of the key feature in the architecture of transformer neural networks.

Read it!