끄적거림

https://arxiv.org/abs/2203.16481 On Uncertainty, Tempering, and Data Augmentation in Bayesian Classification Aleatoric uncertainty captures the inherent randomness of the data, such as measurement noise. In Bayesian regression, we often use a Gaussian observation model, where we control the level of aleatoric uncertainty with a noise variance parameter. By contra arxiv.org cold posterior에 대한 트렌트..