Mass reconstruction with a neural network
(1992) In Physics Letters B 278(1-2). p.181-186- Abstract
A feed-forward neural network method is developed for reconstructing the invariant mass of hadronic jets appearing in a calorimeter. The approach is illustrated in W→qq, where W-bosons are produced in pp reactions at SPS collider energies. The neural network method yields results that are superior to conventional methods. This neural network application differs from the classification ones in the sense that an analog number (the mass) is computed by the network, rather than a binary decision being made. As a by-product our application clearly demonstrates the need for using "intelligent" variables in instances when the amount of training instances is limited.
Please use this url to cite or link to this publication:
https://lup.lub.lu.se/record/fa21e643-fd58-4af2-a681-41ba7de052a9
- author
- Lönnblad, L.
LU
; Peterson, C. LU and Rögnvaldsson, T.
- organization
- publishing date
- 1992-03-19
- type
- Contribution to journal
- publication status
- published
- subject
- in
- Physics Letters B
- volume
- 278
- issue
- 1-2
- pages
- 6 pages
- publisher
- Elsevier
- external identifiers
-
- scopus:1342344350
- ISSN
- 0370-2693
- DOI
- 10.1016/0370-2693(92)90731-I
- language
- English
- LU publication?
- yes
- id
- fa21e643-fd58-4af2-a681-41ba7de052a9
- date added to LUP
- 2019-05-14 16:06:15
- date last changed
- 2024-01-01 04:35:34
@article{fa21e643-fd58-4af2-a681-41ba7de052a9, abstract = {{<p>A feed-forward neural network method is developed for reconstructing the invariant mass of hadronic jets appearing in a calorimeter. The approach is illustrated in W→qq, where W-bosons are produced in pp reactions at SPS collider energies. The neural network method yields results that are superior to conventional methods. This neural network application differs from the classification ones in the sense that an analog number (the mass) is computed by the network, rather than a binary decision being made. As a by-product our application clearly demonstrates the need for using "intelligent" variables in instances when the amount of training instances is limited.</p>}}, author = {{Lönnblad, L. and Peterson, C. and Rögnvaldsson, T.}}, issn = {{0370-2693}}, language = {{eng}}, month = {{03}}, number = {{1-2}}, pages = {{181--186}}, publisher = {{Elsevier}}, series = {{Physics Letters B}}, title = {{Mass reconstruction with a neural network}}, url = {{http://dx.doi.org/10.1016/0370-2693(92)90731-I}}, doi = {{10.1016/0370-2693(92)90731-I}}, volume = {{278}}, year = {{1992}}, }