001484070 000__ 03760cam\\2200589\i\4500
001484070 001__ 1484070
001484070 003__ OCoLC
001484070 005__ 20240117003312.0
001484070 006__ m\\\\\o\\d\\\\\\\\
001484070 007__ cr\cn\nnnunnun
001484070 008__ 231115s2023\\\\sz\a\\\\ob\\\\000\0\eng\d
001484070 019__ $$a1409032539$$a1409203182
001484070 020__ $$a9783031435836$$q(electronic bk.)
001484070 020__ $$a3031435834$$q(electronic bk.)
001484070 020__ $$z9783031435829
001484070 020__ $$z3031435826
001484070 0247_ $$a10.1007/978-3-031-43583-6$$2doi
001484070 035__ $$aSP(OCoLC)1409417758
001484070 040__ $$aGW5XE$$beng$$erda$$epn$$cGW5XE$$dEBLCP$$dYDX$$dOCLCO$$dOCLCQ
001484070 049__ $$aISEA
001484070 050_4 $$aQC793.5.N42
001484070 08204 $$a539.7/215$$223/eng/20231115
001484070 1001_ $$aSutton, Andrew T. C.,$$eauthor.
001484070 24510 $$aDomain generalization with machine learning in the NOvA experiment /$$cAndrew T.C. Sutton.
001484070 264_1 $$aCham :$$bSpringer,$$c[2023]
001484070 264_4 $$c©2023
001484070 300__ $$a1 online resource (xi, 170 pages) :$$billustrations (chiefly color).
001484070 336__ $$atext$$btxt$$2rdacontent
001484070 337__ $$acomputer$$bc$$2rdamedia
001484070 338__ $$aonline resource$$bcr$$2rdacarrier
001484070 4901_ $$aSpringer theses,$$x2190-5061
001484070 500__ $$a"Doctoral thesis accepted by the University of Virginia, USA."
001484070 504__ $$aIncludes bibliographical references.
001484070 5050_ $$aChapter 1: Neutrinos: A Desperate Remedy -- Chapter 2. A Review of Neutrino Physics -- Chapter 3. The NOvA Experiment -- Chapter 4. Event Reconstruction -- Chapter 5. The 3-Flavor Analysis -- Chapter 6. A Long Short-Term Memory Neural Network -- Chapter 7. Domain Generalization by Adversarial Training -- Chapter 8. Conclusion.
001484070 506__ $$aAccess limited to authorized users.
001484070 520__ $$aThis thesis presents significant advances in the use of neural networks to study the properties of neutrinos. Machine learning tools like neural networks (NN) can be used to identify the particle types or determine their energies in detectors such as those used in the NOvA neutrino experiment, which studies changes in a beam of neutrinos as it propagates approximately 800 km through the earth. NOvA relies heavily on simulations of the physics processes and the detector response; these simulations work well, but do not match the real experiment perfectly. Thus, neural networks trained on simulated datasets must include systematic uncertainties that account for possible imperfections in the simulation. This thesis presents the first application in HEP of adversarial domain generalization to a regression neural network. Applying domain generalization to problems with large systematic variations will reduce the impact of uncertainties while avoiding the risk of falsely constraining the phase space. Reducing the impact of systematic uncertainties makes NOvA analysis more robust, and improves the significance of experimental results.
001484070 588__ $$aOnline resource; title from PDF title page (SpringerLink, viewed November 15, 2023).
001484070 650_6 $$aNeutrinos.
001484070 650_6 $$aRéseaux neuronaux (Informatique)
001484070 650_0 $$aNeutrinos.$$0(DLC)sh 85091199
001484070 650_0 $$aNeural networks (Computer science)$$vCongresses$$0(DLC)sh2008108385
001484070 655_0 $$aElectronic books.
001484070 77608 $$iPrint version:$$aSutton, Andrew T. C.$$tDomain Generalization with Machine Learning in the NOvA Experiment$$dCham : Springer International Publishing AG,c2023$$z9783031435829
001484070 830_0 $$aSpringer theses.$$x2190-5061
001484070 852__ $$bebk
001484070 85640 $$3Springer Nature$$uhttps://univsouthin.idm.oclc.org/login?url=https://link.springer.com/10.1007/978-3-031-43583-6$$zOnline Access$$91397441.1
001484070 909CO $$ooai:library.usi.edu:1484070$$pGLOBAL_SET
001484070 980__ $$aBIB
001484070 980__ $$aEBOOK
001484070 982__ $$aEbook
001484070 983__ $$aOnline
001484070 994__ $$a92$$bISE