EPJ Web of Conferences 171, 16005 (2018)
https://doi.org/10.1051/epjconf/201817116005

Identifying QCD Transition Using Deep Learning

¹ Frankfurt Institute for Advanced Studies, 60438 Frankfurt am Main, Germany
² Institut für Theoretische Physik, Goethe Universität, 60438 Frankfurt am Main, Germany
³ Department of Physics, University of California, Berkeley, CA 94720, USA
⁴ Nuclear Science Division, Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
⁵ GSI Helmholtzzentrum für Schwerionenforschung, 64291 Darmstadt, Germany
⁶ Key Laboratory of Quark and Lepton Physics (MOE) and Institute of Particle Physics, Central China Normal University, Wuhan, 430079, China

^* e-mail: zhou@fias.uni-frankfurt.de
^** e-mail: pang@fias.uni-frankfurt.de
^*** e-mail: nansu@fias.uni-frankfurt.de
^**** e-mail: petersen@fias.uni-frankfurt.de
^† e-mail: stoecker@fias.uni-frankfurt.de
^‡ e-mail: xnwang@lbl.gov

Published online: 2 February 2018

Abstract

In this proceeding we review our recent work using supervised learning with a deep convolutional neural network (CNN) to identify the QCD equation of state (EoS) employed in hydrodynamic modeling of heavy-ion collisions given only final-state particle spectra ρ(p_T, Ф). We showed that there is a traceable encoder of the dynamical information from phase structure (EoS) that survives the evolution and exists in the final snapshot, which enables the trained CNN to act as an effective “EoS-meter” in detecting the nature of the QCD transition.