카테고리 없음
Variational Bayesian methods
milab
2019. 8. 3. 01:10
https://en.wikipedia.org/wiki/Variational_Bayesian_methods
Variational Bayesian methods - Wikipedia
Variational Bayesian methods are a family of techniques for approximating intractable integrals arising in Bayesian inference and machine learning. They are typically used in complex statistical models consisting of observed variables (usually termed "data
en.wikipedia.org
https://twiecki.io/blog/2016/06/01/bayesian-deep-learning/
Bayesian Deep Learning
We can see that very close to the decision boundary, our uncertainty as to which label to predict is highest. You can imagine that associating predictions with uncertainty is a critical property for many applications like health care. To further maximize a
twiecki.io