Deep Learning Extraction of Hadron-Hadron Interaction Potentials
A deep-learning framework that treats the recovery of hadron-hadron interaction potentials as an inverse problem and solves it on two fronts: a supervised approach in which deep neural networks learn the inverse mapping from femtoscopy correlation functions (generated with tools like CATS) to parameterized potentials, and an unsupervised approach using symmetric DNNs to construct a model-free potential directly from Lattice-QCD equal-time Nambu-Bethe-Salpeter amplitudes in the HAL QCD framework.
Deep learning for exploring hadron-hadron interactions
In this proceeding, we introduce deep learning technologies for studying hadron-hadron interactions. To extract parameterized hadron interaction potentials from collision experiments, we employ a sup…