Ian Osband
TalkRL: The Reinforcement Learning Podcast
Exploring Joint Prediction and Uncertainty in Neural Networks
The chapter delves into the concept of joint prediction in Bayesian neural networks, discussing the importance of epistemic and alliatoric uncertainties. It compares traditional approaches with the effectiveness of models like EpiNet in making joint predictions, highlighting the shift towards practical performance in decision-making applications.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
