Search found 32 matches
- Wed Feb 09, 2022 2:27 am
- Forum: GeNIe
- Topic: continuous nodes
- Replies: 1
- Views: 1555
continuous nodes
I am trying to create a network with all continuous nodes/some discrete and some continuous. I know that continuous nodes are represented via equations. However the EM algorithm fails for those networks. Does genie's EM works for all continuous nets? and what about hybrid nets? If not, then how are ...
- Tue Feb 08, 2022 2:35 am
- Forum: GeNIe
- Topic: Missing values in test set
- Replies: 1
- Views: 1122
Missing values in test set
Hi, I know that the EM algorithm takes care of missing values in the training set. How do you deal with missing values in the test set? do you simply ignore that specific feature value for that specific sample? or do you do something more sophisticated (assuming I am not actively imputing them or so...
- Mon Jan 24, 2022 11:07 pm
- Forum: GeNIe
- Topic: Influential samples
- Replies: 1
- Views: 1109
Influential samples
Hi,
Does genie have a way of estimating the influence of each training sample on the model? or, a method for finding the most influential training samples? (for example, in the sense that without them prediction will change the most, or model's parameters will change the most).
Thank you.
Does genie have a way of estimating the influence of each training sample on the model? or, a method for finding the most influential training samples? (for example, in the sense that without them prediction will change the most, or model's parameters will change the most).
Thank you.
- Wed Aug 18, 2021 10:06 pm
- Forum: GeNIe
- Topic: EM calculations
- Replies: 1
- Views: 2326
EM calculations
Hi, I wanted to know whether there is any way to obtain some of the internal computations that genie's EM algorithm computes. Specifically, I would like to obtain the probabilities the algorithm computes for each state of each missing entry in the training set, or at least the "expected" s...
- Thu Jun 03, 2021 12:15 am
- Forum: GeNIe
- Topic: Learning parametes in DBNs
- Replies: 7
- Views: 3971
Re: Learning parametes in DBNs
Thanks, you answers do help a lot!
- Thu Jun 03, 2021 12:05 am
- Forum: GeNIe
- Topic: Example network?
- Replies: 1
- Views: 2080
Example network?
Hi, I was wondering whether there are any example-networks (not toy examples) available online as part of the documentation? for instance, is the network described in the sensitivity analysis section available as part of genie's online resources in .xdsl format? (is the dataset used for that network...
- Fri May 28, 2021 9:42 pm
- Forum: GeNIe
- Topic: Learning parametes in DBNs
- Replies: 7
- Views: 3971
Re: Learning parametes in DBNs
Hi Marek, Thanks for the response! I was actually thinking of choosing the most influential variables based on the nodes' colors (very red, lightly red etc). But then I realized that while I understand how the target's "tornado" is being calculated, I am not really sure according to which ...
- Thu May 27, 2021 1:54 am
- Forum: GeNIe
- Topic: Learning parametes in DBNs
- Replies: 7
- Views: 3971
Re: Learning parametes in DBNs
Sorry, I think I found a solution for that, as I can probably unroll the network and then perform SA... However I do have a more fundamental question: I am looking for either the a. "most influential variables", or the b. "most influential tuples of <variables, state>", but what ...
- Thu May 27, 2021 1:19 am
- Forum: GeNIe
- Topic: Learning parametes in DBNs
- Replies: 7
- Views: 3971
Re: Learning parametes in DBNs
Thank you very much Mark.
I see that there is no option to do sensitivity analysis for dbns...may I ask why?
also, is there an alternative you can suggest for SA with regards to DBNs? my goal is just to identify the most influential factors on my target node.
I see that there is no option to do sensitivity analysis for dbns...may I ask why?
also, is there an alternative you can suggest for SA with regards to DBNs? my goal is just to identify the most influential factors on my target node.
- Tue May 25, 2021 1:34 am
- Forum: GeNIe
- Topic: Learning parametes in DBNs
- Replies: 7
- Views: 3971
Learning parametes in DBNs
Hi, I have some questions regarding learning parameters of dynamic BNs. I will talk in terms of intra-slice edges and inter-slice edges though I know genie takes a different representation. 1. I want to be sure that I understand how genie implements training for dbns: lets say that I have 3 training...
- Sat May 22, 2021 7:16 pm
- Forum: GeNIe
- Topic: Learning structure with missing data
- Replies: 11
- Views: 4613
Re: Learning structure with missing data
I see.
Perhaps I should also include in my FS the MB of features with significant number of missing values (like>40% or so).
I cant really find works on that topic, most of the papers talk about MB in the context of "measured" variables.
Thanks Mark.
Perhaps I should also include in my FS the MB of features with significant number of missing values (like>40% or so).
I cant really find works on that topic, most of the papers talk about MB in the context of "measured" variables.
Thanks Mark.
- Sat May 15, 2021 2:27 am
- Forum: GeNIe
- Topic: Learning structure with missing data
- Replies: 11
- Views: 4613
Re: Learning structure with missing data
Thanks mark. I see your point. However, isnt this the case for every FS method? I mean, many FS algos (not just genie's SL) require complete datasets. So obviously if you first impute the missing values and then feed the dataset into the FS algorithm, the FS algorithm (no matter which one) would &qu...
- Mon May 10, 2021 2:18 am
- Forum: GeNIe
- Topic: Learning structure with missing data
- Replies: 11
- Views: 4613
Re: Learning structure with missing data
Politely requesting, perhaps someone can answer my question from my previous message regarding the use of markov blankets for FS in genie?
- Fri May 07, 2021 1:08 am
- Forum: GeNIe
- Topic: Learning structure with missing data
- Replies: 11
- Views: 4613
Re: Learning structure with missing data
Thank you so much for the replies Mark, I really appreciate it. Going back to the FS, regarding the markov-blanket suggestion --- sometime didnt sound right to me and I think I know what it is: In my data I not only have a "latent" target node. I also have other latent variables (i.e i hav...
- Wed May 05, 2021 9:22 pm
- Forum: GeNIe
- Topic: Learning structure with missing data
- Replies: 11
- Views: 4613
Re: Learning structure with missing data
Thank you Mark. Any chance you can answer my first question as well? I know its a bit out of scope but I have been reading mixed research about how is it best to impute values in the training for SL (and FL as well) and each different compelling arguments. I thought that you might have an insight on...