Topics

1

General Discussion / Parameter Learning

« on: May 19, 2023, 18:25:58  »

I have a rather large model built (using structure learning in Hugin) using a large dataset.  I would like to use the same structural model with different data.  For this particular case, I would like to ignore all parameter values learnt from the large dataset.  EM learning starting from the structure with all 1s in the CPTs and zero experience counts seems to be the way to do it, but I do not want to manually replace all experience counts with zero and all entries in the CPTs with 1.  Is there a way to reset CPT entries in bulk?

2

HUGIN GUI Discussion / Variance or Standard Deviation?

« on: February 24, 2023, 01:33:55  »

Greetings to all!

I have a doubt.  Is the "Variance" in the Table for a continuous variable Table for a continuous variable in Hugin actually the Standard Deviation?  I am using Hugin Educational 9.3, in case it matters.

Best regards,

 Marco

3

General Discussion / Excel, Dates, and Discretization

« on: May 03, 2022, 22:15:24  »

I recently ran into a problem that I do not know how to solve in a simple way.  It turns out that Excel automatically turns an entry like 5 - 10 into a date; in this case, May 10.  (I am in the U.S.)  (See https://support.microsoft.com/en-us/office/stop-automatically-changing-numbers-to-dates-452bd2db-cc96-47d1-81e4-72cec11c4ed8)  After discretization of a data set where one of the intervals is 5 - 10, the .cvs file built by Hugin has May 10 entries wherever 5 -10 should be.  Attempts to convert May 10 to 5 - 10 by formatting cells fail, because 5 - 10 is turned into a number representing the number of days from the "beginning of time," and trying to convert that number back to 5 - 10 results in May 10 again.  Does anyone have any suggestions to solve this problem?

4

HUGIN GUI Discussion / Information Entropy Minmization Discretization

« on: August 30, 2021, 20:18:13  »

Greetings!  Could someone please explain in more detail that in the manual what information entropy minimization discretization does? I tried it with a file with 10000 cases generated from the anginaContinuous network in Section 3.3.8 of Jensen and Nielsen's book, discretizing the Therm variable with the Angina variable as target.  It gave reasonable results, with three intervals.  Maybe someone could look at that example and use it to explain which entropy is minimized.

5

HUGIN GUI Discussion / Plate Models

« on: March 22, 2021, 21:55:17  »

Greetings to all.  Is there a way to specify plate models directly in Hugin?  Or, maybe even just repetitive models such as the one in Figure 3.46 in Jensen and Nielsen's 2007 book, _Bayesian Networks and Decision Graphs_, 2nd ed.?

6

HUGIN GUI Discussion / A More General Zoom Feature

« on: March 10, 2021, 21:56:47  »

The Zoom feature of the Hugin is very useful.  Unfortunately, it only affects the size of networks in the network pane.  It would be very useful to have a way to increase the size of all parts of the GUI.  For example: I have to take off my glasses and get very close to the screen to read the names of variables, variable values, and probability values in CPTs.  I have to do the same with the belief bars in run mode.  Is there any fix for this?  If not, is there are any plan to add a more general resize feature?

7

HUGIN GUI Discussion / Temporal Nodes

« on: October 08, 2019, 17:48:51  »

Dear all,

I have been to use temporal nodes in Hugin 8.1 and 8.4.  I do not see a way to specify the number of slices: I get five slices, and that is it.  I suspect that there is a way to change this number, but I cannot see how.  Any help or advice will be welcome.

Best regards,

 Marco

8

General Discussion / Decision Trees

« on: April 24, 2014, 17:45:27  »

Dear Hugin developers and users,

My understanding is that Hugin does not directly support decision trees.  In other words, you can draw a decision tree (with chance, decision, and utility nodes), but there is no way to annotate  the links with probabilities and compute policies within Hugin itself.  Can you confirm?

Best regards,

 Marco