HI
i need to simulate DBN. node D have equation as you can see in the first image but when i unroll DBN equation in node D dose not repeat for other time slice. can you expalin how i can fix it ?
thank you
problem with unrolling DBN
-
- Site Admin
- Posts: 1441
- Joined: Mon Nov 26, 2007 5:51 pm
Re: problem with unrolling DBN
Unfortunately, GeNIe does not support equation nodes in DBNs.
Re: problem with unrolling DBN
HI
so what can i do ?
is it right in bayesian concept that i edit and copy my equation manulally in all of dt Nodes in the unrolled network?
thank you
so what can i do ?
is it right in bayesian concept that i edit and copy my equation manulally in all of dt Nodes in the unrolled network?
thank you
Re: problem with unrolling DBN
hi
no answer ???
no answer ???
-
- Site Admin
- Posts: 436
- Joined: Tue Dec 11, 2007 4:24 pm
Re: problem with unrolling DBN
Hi Bahman,
Most definitely, you can edit the unrolled network any way you please. You can also edit the equations. We do not support equations in DBNs yet but it is a matter of time -- we just haven't had time to do that but we will most certainly return to this issue. Essentially, we need to extend the concept of indexing equations by time, which is, I believe, quite simple. We just had other important priorities. Once we have that, you will be able to construct DBNs with equations. At the moment, you can do it in unrolled networks, making sure that your equations refer to the correct variables.
I hope this helps,
Marek
Most definitely, you can edit the unrolled network any way you please. You can also edit the equations. We do not support equations in DBNs yet but it is a matter of time -- we just haven't had time to do that but we will most certainly return to this issue. Essentially, we need to extend the concept of indexing equations by time, which is, I believe, quite simple. We just had other important priorities. Once we have that, you will be able to construct DBNs with equations. At the moment, you can do it in unrolled networks, making sure that your equations refer to the correct variables.
I hope this helps,
Marek