Generalized Laplace Approximation Improves Bayesian Deep Learning
Researchers introduce a Laplace approximation that embeds tempering in the Hessian for Bayesian deep learning. Experiments show higher accuracy, better calibration. getnews.me/generalized-laplace-appr... #bayesiandeeplearning #laplaceapproximation
It was a great pleasure to host @vincefort.bsky.social to talk about everything #BayesianDeepLearning!
Thanks for the intro @marvinschmitt.com 🙏
What if AI could know when it doesn’t know?
🎙️ @alex-andorra.bsky.social talks with @vincefort.bsky.social about Bayesian deep learning, why it matters for uncertainty, calibration & more
🎧 Tune in: learnbayesstats.com/episode/129-...
#BayesianDeepLearning #MachineLearning #ReliableAI #AIResearch
The #BayesianDeepLearning community developed awesome, efficient methods to estimate an approximation to the posterior distribution of NNs (e.g., Laplace, IVON).
But what do you do once you have done this? Unfortunately, you still need to perform expensive computations when making predictions.
