Research Scientist @DeepMind -- PhD from @UniofOxford
Large language model pretraining. Log scale is my default scale.
Used to be a Leo, now a Gemini.
Joost van Amersfoort @joost_v_amersf
ยท
Apr 29, 2020
Nice write-up of a simple and effective improvement for training your Bayesian NN using Bayes by Backprop!
Paper
Apr 22, 2020
