Thursday, Sep. 14, 2017, 10:30 AM (Beijing Time)  seminar

Identifying QCD transition with Machine Learning
       

Speaker：  Dr. Longgang Pang,Lawrence Berkeley National Laboratory (LBNL)

Date：Thursday, Sep. 14, 2017, 10:30 AM (Beijing Time)

Download：https://pan.baidu.com/s/1geognuz

abstract:

Supervised learning with a deep convolutional neural network is used to identify the QCD equation of state (EoS) employed in relativistic hydrodynamic simulations of heavy-ion collisions from the simulated final-state particle spectra undefinedamp;#961;(pT,undefinedamp;#934;). High-level correlations learned by the neural network act as an effective \"EoS-meter\" in detecting the nature of the QCD transition. The EoS-meter is model independent and insensitive to other simulation inputs, especially the initial conditions. Thus it provides a powerful direct-connection of heavy-ion collision observables with the bulk properties of QCD.

In order to introduce full stack machine learning tools to high energy community, I will also give a wide introduction to traditional machine learning, such as principle component analysis, support vector machine, random decision tree and ensemble method such as random forest and gradient boosting trees as well as basic concepts in deep convolution neural network (DCNN).