Hi all,
My project involves estimating some random vector 'X=[x1,x2....xn]'
using the belief propagation algorithm in Matlab. I have a doubt in the
initialization part of the algorithm.
It states, the initial estimate of each x, x1_hat, x2_hat...xn_hat = mean of
Px(x) and var(x_hat) = var of Px(x) where Px(x) is the prior marginal
distribution. Now how do I do this in Matlab? If I assume some prior marginal as
U(0,1), then what is my initial x1_hat, x2_hat...xn_hat ?. I understand it
theoretically but its difficult to transform it to coding domain.
Your reply would be of great help to proceed in my project. Thanks a lot in
advance !
Regards,
Mahadevi.
