Deep learning and AdS/QCD
Deep learning and AdS/QCD
复制标题
深度学习和ADS/QCD
DOI：
10.1103/physrevd.102.026020
复制
发表时间：
2020-05
影响因子：
5
通讯作者：
Tetsuya Akutagawa;K. Hashimoto;Takayuki Sumimoto
中科院分区：
文献类型：
--
作者：
Tetsuya Akutagawa;K. Hashimoto;Takayuki Sumimoto
我们提出了一种深度学习方法，从强子谱数据中构建AdS/QCD模型。通用AdS/QCD模型的一个主要问题是，一个大的模糊性是允许与全息计算QCD观测量的体重力度规。我们采用实验测量的ρ介子和α 2介子的光谱作为训练数据，并进行监督机器学习，具体确定AdS/QCD模型的体度规和介子轮廓。我们的深度学习（DL）架构基于AdS/DL对应关系[K. Hashimoto，S. Sugishita，A. Tanaka，和A. Tomiya，Phys. Rev. D 98，046019（2018）PRVDAQ 2470 -001010.1103/PhysRevD.98.046019]，其中深度神经网络与涌现的大块时空相一致。
We propose a deep learning method to build an AdS/QCD model from the data of hadron spectra. A major problem of generic AdS/QCD models is that a large ambiguity is allowed for the bulk gravity metric with which QCD observables are holographically calculated. We adopt the experimentally measured spectra of ρ and a2 mesons as training data, and perform a supervised machine learning which determines concretely a bulk metric and a dilaton profile of an AdS/QCD model. Our deep learning (DL) architecture is based on the AdS/DL correspondence [K. Hashimoto, S. Sugishita, A. Tanaka, and A. Tomiya, Phys. Rev. D 98, 046019 (2018)PRVDAQ2470-001010.1103/PhysRevD.98.046019] where the deep neural network is identified with the emergent bulk spacetime.