BayesFusion Support Forum

Thanks.

Could anyone provide more information on noisy-adder such as a paper by Adam Zagorecki and Marek Druzdzel "The noisy-average model for local probability distribution" (which is on Researchgate but I don't have an access without an edu email). I am quite confused by GeNIe's noisy-adder node...

Hi administrator

Why setting virtual evidence for a node that has child nodes has no effect? If the node has no child node everything is all right.

Thanks

Charlie

Thanks. It's my ignorance. I thought once the nodes in the submodel window were dropped back to the main window the submodel node in the main window will automatically disappear. It's OK.
Charlie

Hi Marek Thanks for the advice - very helpful, except I had no success in dragging and dropping nodes in a submodel window to the main network's window. Here was how I did: vertically tiled the two windows, select all the elements in the submodel window, and move them across to the main window. The ...

Hi administrator I packed a part of a net into a submodel node. Is there any way to unpack the nodes in the submodel back to the main net? When a node gets packed into a submodel, its relations with child and parent nodes can no longer be seen in the submodel window. I found this very inconvenient, ...

Indeed. Thank you.

shooltz[BayesFusion] wrote: ↑Thu Feb 28, 2019 8:51 pm GeNIe 2.3.3828 (available now) fixes the issues reported in this forum thread.

Hi Marek

I really wish the new service release with the bug fixed could be made available asap. There is a current opportunity for me to demonstrate the power of GeNIe with hybrid net, to my coworkers and managers.

Thanks

Charlie

Thank you Marek for the response. Really appreciate it.
Charlie

I now realized a problem associated with checking "reject out-of-bound and invalid sample" in Network Property - in a hybrid model, a child discrete chance node (as the "test" node in the attached example) won't get the probabilities of all of its states added to 100%. In the att...

On the previous thread of discussion with GeNIe administrators, I summarize here the way I make a truncated distribution - hopefully of some reference value to others who have a similar need. The need: to truncate a distribution of any form including a user-defined, at a cutoff which may be a fixed ...

With your advice, I now realized that the problem with the net I sent first is that GeNIe samples outside the lower bound which was 1 (upper bound being 10) in my case and doesn't cast those samples at zero. with the net I sent next is that TruncNormal doesn't allow "cutoff" to go beyond t...

Thank you so much for the detailed explanation. The suggested solution of rejecting out-of-bound and invalid samples also works well - a great feature.

Charlie

Thank you. TruncNormal does appear to be the solution. But please see the attached net: a TruncNormal node fed with a stochastic threshold node for its min parameter. The threshold node's distribution starts at 3. The "test" chance node is to verify whether the CPT correctly reflects the t...

Thank you for the explanation.
Charlie