Using neural networks to identify jets
(1991) In Nuclear Physics, Section B 349(3). p.675-702- Abstract
A neural network method for identifying the ancestor of a hadron jet is presented. The idea is to find an efficient mapping between certain observed hadronic kinematical variables and the quark-gluon identity. This is done with a neuronic expansion in terms of a network of sigmoidal functions using a gradient descent procedure, where the errors are back-propagated through the network. With this method we are able to separate gluon from quark jets originating from Monte Carlo generated e+e- events with ≈85% approach. The result is independent of the MC model used. This approach for isolating the gluon jet is then used to study the so-called string effect. In addition, heavy quarks (b and c) in... (More)
A neural network method for identifying the ancestor of a hadron jet is presented. The idea is to find an efficient mapping between certain observed hadronic kinematical variables and the quark-gluon identity. This is done with a neuronic expansion in terms of a network of sigmoidal functions using a gradient descent procedure, where the errors are back-propagated through the network. With this method we are able to separate gluon from quark jets originating from Monte Carlo generated e+e- events with ≈85% approach. The result is independent of the MC model used. This approach for isolating the gluon jet is then used to study the so-called string effect. In addition, heavy quarks (b and c) in e+e- reactions can be identified on the 50% level by just observing the hadrons. In particular we are able to separate b-quarks with an efficiency and purity, which is comparable with what is expected from vertex detectors. We also speculate on how the neutral network method can be used to disentangle different hadronization schemes by compressing the dimensionality of the state space of hadrons.
(Less)
- author
- Lönnblad, Leif LU ; Peterson, Carsten LU and Rögnvaldsson, Thorsteinn
- organization
- publishing date
- 1991-02-11
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Nuclear Physics, Section B
- volume
- 349
- issue
- 3
- pages
- 28 pages
- publisher
- North-Holland
- external identifiers
-
- scopus:0041834419
- ISSN
- 0550-3213
- DOI
- 10.1016/0550-3213(91)90392-B
- language
- English
- LU publication?
- yes
- id
- 821fbd3e-e4c5-4013-95f3-b45da15dab63
- date added to LUP
- 2019-05-15 07:55:53
- date last changed
- 2024-01-01 04:41:00
@article{821fbd3e-e4c5-4013-95f3-b45da15dab63, abstract = {{<p>A neural network method for identifying the ancestor of a hadron jet is presented. The idea is to find an efficient mapping between certain observed hadronic kinematical variables and the quark-gluon identity. This is done with a neuronic expansion in terms of a network of sigmoidal functions using a gradient descent procedure, where the errors are back-propagated through the network. With this method we are able to separate gluon from quark jets originating from Monte Carlo generated e<sup>+</sup>e<sup>-</sup> events with ≈85% approach. The result is independent of the MC model used. This approach for isolating the gluon jet is then used to study the so-called string effect. In addition, heavy quarks (b and c) in e<sup>+</sup>e<sup>-</sup> reactions can be identified on the 50% level by just observing the hadrons. In particular we are able to separate b-quarks with an efficiency and purity, which is comparable with what is expected from vertex detectors. We also speculate on how the neutral network method can be used to disentangle different hadronization schemes by compressing the dimensionality of the state space of hadrons.</p>}}, author = {{Lönnblad, Leif and Peterson, Carsten and Rögnvaldsson, Thorsteinn}}, issn = {{0550-3213}}, language = {{eng}}, month = {{02}}, number = {{3}}, pages = {{675--702}}, publisher = {{North-Holland}}, series = {{Nuclear Physics, Section B}}, title = {{Using neural networks to identify jets}}, url = {{http://dx.doi.org/10.1016/0550-3213(91)90392-B}}, doi = {{10.1016/0550-3213(91)90392-B}}, volume = {{349}}, year = {{1991}}, }