Noisy-max marginalisation bug

The engine.
Post Reply
adam
Posts: 25
Joined: Thu Jan 17, 2008 11:01 pm
Location: Shrivenham, UK
Contact:

Noisy-max marginalisation bug

Post by adam »

Hi,

I just wanted to report a bug in GeNIe/SMILE: 'marginalize' option fails for the case of a noisy-max node.

Original network had 3 parents to the noisy-max node, I selected option 'marginalize' on one of the parents. In the result the noisy-max parameters (leak) got totally corrupted, as can be seen below. Happy to assist to get things right ;) ... and stay safe.

Adam

noisy-max-failure.png
noisy-max-failure.png (107.17 KiB) Viewed 3289 times
shooltz[BayesFusion]
Site Admin
Posts: 1417
Joined: Mon Nov 26, 2007 5:51 pm

Re: Noisy-max marginalisation bug

Post by shooltz[BayesFusion] »

We were able to reproduce the problem; new GeNIe build with a fix will be released soon.
shooltz[BayesFusion]
Site Admin
Posts: 1417
Joined: Mon Nov 26, 2007 5:51 pm

Re: Noisy-max marginalisation bug

Post by shooltz[BayesFusion] »

We have fixed this problem in GeNIe 3.0.5905, which is now available for download.

We decided to implement the fix by changing the types of the children of the marginalized node to CPT. The reason for this is that the children are losing the incoming arc to the marginalized node (which is deleted), but can also get new incoming arcs. In general case this may break the CI constraint on the noisy nodes, therefore the only way to handle the problem is to convert the node to conditional probability table.
Post Reply