Reply
Tue 29 Nov, 2011 09:39 pm
Context:
Background knowledge is encoded through a
constrained space of hypotheses about pos-H
sible values for the latent variables, candidate
worldstructuresthatcouldexplaintheobserved
data.Finer-grainedknowledgecomesinthe“prior
probability” (h ),thelearner’sdegreeofbeliefinP h
a specific hypothesis prior to (or independenth
of) the observations. Bayes’s rule updates priors
to “posterior probabilities” ( h|d ) conditional onP hd
the observed data :d
@oristarA,
I would say it means AND such as: probability (A,) probability (B), probability (A AND B).
@Zarathustra,
Zarathustra wrote:
I would say it means AND such as: probability (A,) probability (B), probability (A AND B).
Excellent!
Sounds you're very familiar with mathematics?