Closed giopaglia closed 8 months ago
Hi,
I didn't notice that you had already posted these, so also made some timestamps myself. Your timestamp descriptions are better though, so I'll leave mine out. (Except for 05:02 - I think "Applications" as in your slide title, or "Real-world Applications", would be a better description for that part.)
I also collected the links to the papers mentioned at 05:02, so I'll post them below:
Links to citations:
https://drops.dagstuhl.de/opus/volltexte/2021/14783/ - Interval Temporal Random Forests with an Application to COVID-19 Diagnosis
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4102488 - The Voice of COVID19: Breath and Cough Recording Classification with Temporal Decision Trees and Random Forests
https://arxiv.org/abs/2109.08325 - Decision Tree Learning with Spatial Modal Logics
https://link.springer.com/chapter/10.1007/978-3-031-06242-1_53 - Statistical and Symbolic Neuroaesthetics Rules Extraction from EEG Signals
Right, "Applications" seems more pertinent indeed :) Thanks for collecting the links, is it possible to have them listed in the video description? Also, I have two more questions about the YouTube video:
Thanks for collecting the links, is it possible to have them listed in the video description?
That's my hope, to have them in the video description before the timestamp section. But it's for @logankilpatrick/the Julia YouTube team to decide - I'm just a volunteer posting the timestamps as I go back and watch the JuliaCon talks I missed.
Regarding the comment, if the comment contained a link in it, it may be a victim of YouTube's "spam detection" algorithm - it's kind finicky and unpredictable about what links it allows and disallows. But Logan or someone else on the admin side of the account might have a better answer to that.
Speaking of links, I forgot to add the repo link in the previous comment, so:
ModalDecisionTrees on Github: https://github.com/giopaglia/ModalDecisionTrees.jl
I try to bring this GItHub repo back to life. I don't have access to YT channel, I just normal user, but I will try what I can to make whole topic alive.
I combined timestamps and materials mentioned in this thread into text below.
Contents 00:00 Opening and introduction 00:44 Symbolic Learning & the importance of interpretability 01:29 Standard Decision Trees can't natively deal with temporal/spatial data 02:02 Modal logics are tailored for temporal/spatial reasoning 03:00 Example: how a Modal Decision Tree would classify an image 04:06 ModalDecisionTrees.jl: features & limitations 05:02 Performances 05:45 Live demo!
Resources ModalDecisionTrees.jl Federico Manzella, Giovanni Pagliarini, Guido Sciavicco, Ionel Eduard Stan, Interval Temporal Random Forests with an Application to COVID-19 Diagnosis Guido Sciavicco, Federico Manzella, Giovanni Pagliarini, Ionel Eduard Stan, The Voice of COVID19: Breath and Cough Recording Classification with Temporal Decision Trees and Random Forests Giovanni Pagliarini, Guido Sciavicco, Decision Tree Learning with Spatial Modal Logics M. Coccagna, F. Manzella, S. Mazzacane, G. Pagliarini, G. Sciavicco, Statistical and Symbolic Neuroaesthetics Rules Extraction from EEG Signals
Thank you all, here's an updated version.
Contents
Resources
In last post in this thread on Julia Discourse they said, that someone is working to bring this repo back to life. At this moment normal users like my can only wait for what will happened.
Thank you. Timestamps were added to the video, we will close this issue, when we get access rights to this GitHub repository.
We are now can close the issue.
Speaker: Giovanni Pagliarini Video URL: https://www.youtube.com/watch?v=8F1vZsl8Zvg
00:06 Introduction 00:44 Symbolic Learning & the importance of interpretability 01:29 Standard Decision Trees can't natively deal with temporal/spatial data 02:02 Modal logics are tailored for temporal/spatial reasoning 03:00 Example: how a Modal Decision Tree would classify an image 04:06 ModalDecisionTrees.jl: features & limitations 05:02 Performances 05:45 Live demo!
Merci! :)