A fair amount; I've seen some of his work and I think it's pretty good. I don't really like Octave (his program of choice), but I understand why he used it. I would have gone with something higher-level, since a lot of decent tools are out there that add a layer of abstraction to ML.
Anyway, I consider Bayesian logic a cornerstone of ML modeling. It's not so much the content that needs to be memorized/understood as much as it is the way of thinking that Bayesian methodologies present over frequentist statistics.
