Whiteboard from today's meeting on Bayesian ML:
Cox: P(A, B) = P(A|B)P(B) = P(B|A)P(A)
=>
P(A|B) = [P(B|A)P(A)] / P(B) (Bayes)
The ML model needs to be a generative model - statistically model that generate data
Example - a mixture of normal distribution. Two normal distributions. You choose which one you use in probability 1/2 and then you use to generate data.
(n+1)! = (n+1)(n)!
https://en.wikipedia.org/wiki/Conjugate_prior
No comments:
Post a Comment