BayesFusion Support Forum

Setting a virtual evidence on a discrete node with no parents will cause discretisation. The implementation of virtual evidence in SMILE creates a temporary child node for each node with virtual evidence. The temporary child node has a 2-state CPT populated with numbers specified for virtual evidenc...

Is there any missing data items in the learning data set? In GeNIe 4.0 when the data is complete, the EM procedure switches to simple counting, regardless of the parameter initialization.

Can you send a direct link to the API documentation with the requested endpoint stated The direct link to the documentation page is: https://support.bayesfusion.com/docs/Wrappers/python.html If Pythonanywhere's allowlist is updated, do you plan to use pip with --index-url option to install PySMILE ...

I'm not sure if I fully understand your question. The API documentation links for PySMILE are as follows: PDF version: https://support.bayesfusion.com/docs/Wrappers.pdf HTML version: https://support.bayesfusion.com/docs/Wrappers Regarding the academic PySMILE binaries, we publish Python wheels at ht...

I was wondering if it is possible to identify which specific cases were misdiagnosed/misclassified. If you specify a name for the validation output file, the validation will produce a dataset based on the input data with additional columns added. There will be one column for each class node, contai...

Please check your PMs.

You can reduce the max entropy/cost ratio (the dropdown in the upper-right corner of the diagnosis window), then use the E/C slider to move the alpha to a very low value. You should see your observations appear back in black (because alpha close to zero should make the cost influence vanish in the e...

Is it (or when will it be) possible to run the diagnosis function in BayesMobile for Discrete Models? Just to clarify: BayesMobile main functionality is actually running diagnosis with discrete models. You can create a diagnostic model in GeNIe, test the diagnostic output in GeNIe, then upload the ...

seems GeNie doesn't much care for working through a ~32k node network... If GeNIe performs inadequately, maybe you can share your model? Send me a private forum message if this is possible. We will profile and pinpoint the hotspots. but is there a known network size limit? It's quite hard to establ...

NOT BENEFICIAL is displayed when the diagnostic value of the observation is negative. The negative value can be calculated when the observation has an associated cost. The actual formula is V = cross-entropy - alpha * costs where alpha is the entropy/cost ratio, which you can modify in GeNIe's diagn...

You can now set the barchart view for the nodes. In C++, use DSL_screenInfo's data members barchartActive, barchartWidth and barchartHeight. DSL_node *node = ... DSL_screenInfo &scr = node->Info().Screen(); scr.barchartActive = true; scr.barchartWidth = 200; scr.barchartHeight = 500; PySMILE has...

You can load your own models into BayesMobile after $9.99 in-app purchase (payments are handled by Apple Store). Click on the "Use Your Model" option on the main application screen. Please note that the .xdsl file should be on your device already.

The revised manual for SMILE 2.0 (the core C++ library) is available at https://support.bayesfusion.com/docs/
Enjoy! :)

You can use your existing code with SMILE 2.0. We're preparing the documentation refresh.

If you can, send me a link or a .zip with the complete project to my email address. We'll try to reproduce/fix the problem.