Question: Given a dataset {x 1 ; x 2 ; : : : ; x n } containing samples drawn from an unknown data distribution p(x),
Given a dataset {x1; x2; : : : ; xn }containing samples drawn from an unknown data distribution p(x), we want to learn a distribution p
(x) that is as close as possible to the true distribution p(x). Consider two cost functions to find the optimal p
(x): DKL(p(x)I p
(x)) and
x (p
(x) p(x))2dx. Choose the best cost function out of these.
Transcribed image text
Step by Step Solution
There are 3 Steps involved in it
Get step-by-step solutions from verified subject matter experts
