BayesFusion Support Forum

You should pass the full .zip file name to install.packages and use the 'type' parameter: > install.packages("C:/Users/your-user-id/Downloads/rSMILE_2.0.8.zip", repos = NULL, type = "win.binary") package 'rSMILE' successfully unpacked and MD5 sums checked The example above assume...

is it possible to call the hybrid network in R using rSMILE and then connect it to a global sensitivity analysis package in R

We don't have any experience with R's sensitivity analysis packages. Can you post a link to the package you're referring to?

In GeNIe 4.0 we have modified the inference algorithm for the hybrid models. Instead of a complete discretized copy (which you can get in GeNIe 3.x), we use 'virtualized' CPTs for equation nodes. Additionally, we always take into account all possible reductions in the CPTs, such as the presence of t...

We were able to reproduce this using a different compiler, so it's clearly a SMILE 2.0.x bug. I'll send you a link to a private build once the fix is ready.

64-bit GeNIe can be now downloaded as a 'classic' EXE or MSI (Microsoft Installer) package. The MSI setup will work with macOS and Wine, including the most recent macOS versions which only allow 64-bit software to run. MSI setup is also available for GeNie Academic. To use 32-bit GeNIe (including Ge...

We have fixed multiple bugs related to copy/paste recently, if you can, please try to reproduce this problem using the most recent build 4.0.2221.

This issue was fixed in the most recent release (4.0.2221).

This bug was fixed in the most recent release (4.0.2221).

The most recent build (4.0.2221) will stop switching the pursued fault once you manually select your fault. There's no explicit option to control this in the UI, but we believe the new approach will work in all diagnostic scenarios.

We have just released two online tools for exploring probability distributions:

Probability Distribution Visualizer
https://prob.bayesfusion.com

Metalog Builder:
https://metalog.bayesfusion.com

Send you an email with a link to a private GeNIe build, which implements monochrome bars.

We don't support per-node bar colors in GeNIe at this point. We were considering a global option to display bars in monochrome - would that be helpful to you?

Can you share the source code and your model in the text format? You can use the private messaging on this forum if you don't want these to be publicly accessible.

At this point we only support cross validation in discrete Bayesian networks.

See the Tutorial2.java program in SMILE Wrappers Manual. The static functions printAllPosteriors and printPosteriors demonstrate how to access the calculated probability values.

All our documentation is available at https://support.bayesfusion.com/docs/