As a consequence, there is a choice between Mean vs Mode-seeking behaviour

"One of the best programming skills you can have is knowing when to walk away for awhile." -Oscar Godson #WednesdayWisdom

Our team ApproxBayes has a new webpage. Check it out at team-approx-bayes.github.io

Our lab recently presented past and ongoing work in the RIKEN AIP open seminar series. It was a pleasure to take part! My slides: dvtailor.github.io/pres/mem-exp/r…

Evidence suggests psychedelics induce more uniform distribution over prior beliefs in the world. The resemblance between psychedelic-induced hallucinations and CNN filter visualisations is widely observed. Should we be looking to embed more human-like priors in artificial nets?

Today (Monday) I will be at the panel of "I can't believe it's better" NeurIPS Conference conf …cant-believe-its-not-better.github.io/neurips2021/sc… Tomorrow (Tuesday), I will give a talk with Dharmesh Tailor Siddharth Swaroop on "Adaptive and Robust learning with Bayes" at the BDL workshop bayesiandeeplearning.org 1/2

Big thanks to ProbAI — 2025 ✌️ for bringing together such a great lineup of lecturers. The in-person format makes a huge difference to coping with the packed schedule, looking forward to seeing more events in the future!

It is my pleasure to announce the 2nd Bayes-Duality workshop, focusing on the design of AI that learns adaptively, robustly, and coninually, like humans. bayesduality.github.io/workshop_2024.… You can watch all 26 talks through zoom livestream (June 12-21). Register at …c59ed978213830355fc8978.doorkeeper.jp/events/172217