Off-the-shelf deep learning is not enough,and requires parsimony,Bayesianity,and causality  

作　　者：Rama K.Vasudevan Maxim Ziatdinov Lukas Vlcek Sergei.V.Kalinin 

机构地区：[1]Center for Nanophase Materials Sciences,Oak Ridge,TN 37831,USA [2]Computational Sciences and Engineering Division,Oak Ridge,TN 37831,USA [3]Materials Science and Technology Division,Oak Ridge National Laboratory,Oak Ridge,TN 37831,USA [4]Present address:Bayer,St.Louis,MO 63141,USA

出　　处：《npj Computational Materials》2021年第1期133-138,共6页计算材料学（英文）

基　　金：The work was supported by the U.S.Department of Energy,Office of Science,Materials Sciences and Engineering Division(S.V.K.,L.V.,R.K.V.).

摘　　要：Deep neural networks(‘deep learning’)have emerged as a technology of choice to tackle problems in speech recognition,computer vision,finance,etc.However,adoption of deep learning in physical domains brings substantial challenges stemming from the correlative nature of deep learning methods compared to the causal,hypothesis driven nature of modern science.We argue that the broad adoption of Bayesian methods incorporating prior knowledge,development of solutions with incorporated physical constraints and parsimonious structural descriptors and generative models,and ultimately adoption of causal models,offers a path forward for fundamental and applied research.

关 键 词：learning ENOUGH FINANCE 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]