If one is a true Bayesian, one should be able to define an appropriate sigma-algebra before assigning probabilities

My personal favorites of 2023 (no particular order): 1) Heavener by Invent Animate 2) Shrine by Bleed From Within 3) Death Below by August Burns Red 4) The death We Seek by Currents

I'm teaching a new time series course this term, so I've written some new lecture notes. This was my first non-trivial bit of writing using #quarto. Would recommend. Will do again. darrenjw.github.io/time-series/

❄️

SNE and t-SNE perform dimensionality reduction by minimizing relative entropy (KL) between high and low dimensional spaces. t-SNE improves over SNE by replacing Gaussians with students’ t-distributions in the low dimensional space. en.wikipedia.org/wiki/T-distrib…

I'm attending Google Developer Groups GDG Cloud Mexico City w/ Build with AI on Jun 10, 2024.

Nothing beats the 2000’s metalcore sound 🧘 open.spotify.com/track/1oe7vtdn…

Hey there! I start here a series of posts around the ups and downs of building AI products. I’ve been thinking for a long time about writing about this topic and I’ve finally taken the plunge. Hope you like it! linkedin.com/pulse/complex-…

I just found out about this website. It's a database on incidents in the AI landscape. I think I just found out how to battle doomscrolling 🤣 incidentdatabase.ai

LIVE now! Matt Garman, AWS CEO, delivers the AWS reInvent 2025 Opening Keynote with updates on how AWS is moving the cloud forward. Join now: go.aws/3XPt8NH