no code implementations • 12 Aug 2021 • Yu Huang, James Li, Min Shi, Hanqi Zhuang, Xingquan Zhu, Laurent Chérubin, James VanZwieten, Yufei Tang
A spatio-temporal physics-coupled neural network (ST-PCNN) model is proposed to achieve three goals: (1) learning the underlying physics parameters, (2) transition of local information between spatio-temporal regions, and (3) forecasting future values for the dynamical system.
no code implementations • 18 May 2018 • Cheng Ju, James Li, Bram Wasti, Shengbo Guo
We show that the HELP algorithm improves the predictive performance across multiple tasks, together with semantically meaningful embedding that are discriminative for downstream classification or regression tasks.
no code implementations • 31 Oct 2014 • Ya Le, Eric Bax, Nicola Barbieri, David Garcia Soriano, Jitesh Mehta, James Li
We introduce a technique to compute probably approximately correct (PAC) bounds on precision and recall for matching algorithms.