Using complementary priors to eliminate explaining away

• A “complementary” prior is defined as one that exactly cancels the correlations created by explaining away. So the posterior factors. – Under what conditions do complementary priors exist? – Is there a simple way to compute the product of the likelihood term and the prior term from the data? • Yes!  In one kind of sigmoid belief net, we can simply use

hidden variables

hidden variables

prior

hidden variables

likelihood

data