Speaker
勋 陈(Central China Normal University)
Description
In this talk, I will present the application of machine learning in holographic QCD. By incorporating the equation of state and baryon number susceptibility data, we leverage machine learning techniques to construct a holographic model capable of predicting the location of the critical endpoint (CEP). Furthermore, we enhance the model using Bayesian inference, providing a refined CEP prediction that accounts for uncertainties from lattice QCD. Additionally, we apply the constructed model to compute various physical observables, including transport properties and the heavy quark potential.
Author
勋 陈(Central China Normal University)
Co-authors
Mei HUANG Mei(IHEP, CAS)
Prof.Kai Zhou(香港中文大学(深圳))