I'm reading this for fun -- tutorials and book recommendations on the Bayesian methods toolboox with a cognitive science/machine learning slant. Comes from the Computational Cognitive Science Lab at Berkeley. I recommend the general 2008 tutorial.
Useful stuff included in tutorial:
Parameter estimation
Model selection
Why Occam's Razor emerges naturally from the Conservation of Expected Evidence
Graphical models
Hierarchical Bayesian models
Once (generic *)you finish the list (or feel competent at the math-heavy stuff on it, anyway) I recommend reading up on Bayesian nonparametric methods. I'm particularly fond of Gaussian process regression.
I like this source for Bayesian nonparametrics; the disadvantage is that it's mostly scribe notes, but a lot of the referenced papers are well-written and explain important material.
Out of professional curiosity, what is the focus of your research? (I'm a postdoc statistician at the Ottawa Institute of Systems Biology.)
Not completely defined at the moment since I'm a 1st year PhD student at NYU, and currently doing rotations. It'll be something like comparative genomics/regulatory networks to study evolution of bacteria or perhaps communities of bacteria.
Then you may be interested in the research of Michael I. Jordan. (The computational biology link will probably be the most useful to you, but as you can see from the diversity of applications, he's quite the generalist.)
For Bayesian networks you can probably to better than Pearl. Adnan Darwiche or Daphne Koller's books are better textbooks, unless you're interested specifically in causality.
I like this source for Bayesian nonparametrics; the disadvantage is that it's mostly scribe notes, but a lot of the referenced papers are well-written and explain important material.
EDIT: This was supposed to be a reply to Cyan's post.
AWesome, thanks!