We have restored access to the website from outside the CERN network, however access from certain worldwide locations is still being blocked (read more here).

CERN Accelerating science

Home > Recursive Neural Networks in Quark/Gluon Tagging
 
Talk
Title Recursive Neural Networks in Quark/Gluon Tagging
Video
If you experience any problem watching the video, click the download button below
Download Embed
Mp4:Medium
(1000 kbps)		High
(4000 kbps)		More..
Copy-paste this code into your page:
Copy-paste this code into your page to include both slides and lecture:
Author(s) Cheng, Taoli (speaker) (University of Chinese Academy of Sciences)
Corporate author(s) CERN. Geneva
Imprint 2018-04-11. - 0:32:10.
Series (Machine Learning)
(2nd IML Machine Learning Workshop)
Lecture note on 2018-04-11T11:25:00
Subject category Machine Learning
Abstract Vidyo contribution Based on the natural tree-like structure of jet sequential clustering, the recursive neural networks (RecNNs) embed jet clustering history recursively as in natural language processing. We explore the performance of RecNN in quark/gluon discrimination. The results show that RecNNs work better than the baseline BDT by a few percent in gluon rejection at the working point of 50\% quark acceptance. We also experimented on some relevant aspects which might influence the performance of networks. It shows that even only particle flow identification as input feature without any extra information on momentum or angular position is already giving a fairly good result, which indicates that most of the information for q/g discrimination is already included in the tree-structure itself.
Copyright/License © 2018-2024 CERN
Submitted by paul.seyfert@cern.ch

 


 Record created 2018-04-12, last modified 2022-11-02
Similar records


External links:
Download fulltextTalk details
Download fulltextEvent details