Calculate MPE in SMILE?

[JeffV]

Is there a way to directly calculate the Most Probable Explanation after setting evidence in SMILE? I've done this in Genie, but I couldn't find anything in the SMILE documentation about directly calculating this, as opposed to calculating a full probability distribution and picking the state with the highest probability. Or is this the only option? Thanks!

[shooltz[BayesFusion]]

It's possible, but there's no documentation. See DSL_network::AnnealedMap in network.h for the method signature. The inputs and outputs are closely related to GeNIe's MAP dialog.