What if AI could know when it doesn’t know?

🎙️ Alex Andorra talks with Vincent Fortuin about Bayesian deep learning—why it matters for uncertainty, calibration, and real-world reliability.

🎧 Tune in: https://learnbayesstats.com/episode/129-bayesian-deep-learning-ai-for-science-vincent-fortuin

#BayesianDeepLearning #MachineLearning #ReliableAI #AIResearch

🤔 Variational learning is often thought to be impractical
🔥 Plot twist: it actually works better than Adam!

Meet IVON, a new optimizer that brings the best out of variational learning – 🧵 (1/9)

📰 https://arxiv.org/abs/2402.17641

#NLProc #ICML2024 #DeepLearning #VariationalLearning #BayesianDeepLearning