Become a member
Sign in
Brandon Gomes
Brandon Gomes

Brandon Gomes

4 Following
3 Followers
  • Profile
  • Highlights

Highlighted by Brandon Gomes

See more

From Bayesian Neural Network Series Post 2: Background Knowledge by Kumar Shridhar

Uncertainties can be estimated by placing a probability distributions over either the model parameters or model outputs. Epistemic uncertainty is modeled by placing a prior distribution over a model’s weights and then trying to capture how much these weights vary given some data. Aleatoric uncertainty, on the other hand, is modeled by placing a distribution over the output of the model.