By the end of this lecture
Four things you can do.
Read a distribution over worlds
Probabilistic facts, total choices, world weights, and a query probability that sums over worlds.
Open the four systems
Say what DeepProbLog, NeurASP, Scallop and ULLER each put inside the computation graph.
Price exact inference
Explain weighted model counting, the #P-hardness, and why compilation changes the cost but not the problem.
Separate loss from architecture
State the difference in one sentence and two equations, and name the gradient failure modes.