Timeline for What is the meaning of calculating Maximum Likelihood from complete data for Bayesian Nework paremeter learning?
Current License: CC BY-SA 4.0
8 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Jul 9, 2019 at 19:21 | vote | accept | xabzakabecd | ||
| Jul 9, 2019 at 18:43 | comment | added | PauZen | You can begin with a structure. Especially when you do local search its quite easy to understand. You begin with your structure then you try to improve. | |
| Jul 9, 2019 at 15:49 | comment | added | xabzakabecd | You helped me more than a lot. I don't know if I can ask you just one more thing. Is bayesian network structure learning done when we don't know the structure or we can do this even when we have a network structure from the given data to find the optimal structure? Or can we do structural learning for both cases? I am just exposed to this subject and trying to understand it. Many thanks! | |
| Jul 9, 2019 at 12:39 | comment | added | PauZen | in video 12.a around 7 minutes, he explain the minium spanning tree. This is what i told you for the method b. Its a good beginning to initialize the structure of your direct acyclic graph. Around 23 min (video 12.a) he expose the score with penalization (AIC here if i look well). Between he just show that maximizing likelihood gives you the best structure (and you need penalization to not overfit as always). After in video 12.b he expose local search and greedy search algorithm (what is method b in my post) then he expose method a (around the mid of video). Hope it helps. | |
| Jul 9, 2019 at 5:51 | comment | added | xabzakabecd | This is the link to the lecture I am looking at:youtube.com/… Videos from 11a to 12b in the playlist are what I have seen and had questions in my mind. Thank you for your detailed explanations and time. I don't know if you can take a look at them. Many thanks to you. | |
| Jul 8, 2019 at 23:14 | history | edited | PauZen | CC BY-SA 4.0 |
added 2320 characters in body
|
| Jul 8, 2019 at 12:29 | comment | added | xabzakabecd | I have just added some more detail on my question. | |
| Jul 8, 2019 at 11:13 | history | answered | PauZen | CC BY-SA 4.0 |