Attribute driven inverse materials design using deep learning Bayesian framework

作     者：Piyush M.Tagade Shashishekar P.Adiga Shanthi Pandian Min Sik Park Krishnan S.Hariharan Subramanya Mayya Kolake 

作者机构：Next Gen ResearchSamsung Advanced Institute of TechnologySamsung R&D InstituteBangalore 560037India Autonomous Material Development LabSamsung Electronics130 Samsung-roSuwonGyeonggi-do 443-803Republic of Korea 

出 版 物：《npj Computational Materials》 (计算材料学（英文）)

年 卷 期：2019年第5卷第1期

页      面：22-35页

核心收录：

学科分类：0502[文学-外国语言文学] 050201[文学-英语语言文学] 05[文学] 

主　　题：inverse learning enough 

摘      要：Much of computational materials science has focused on fast and accurate forward predictions of materials properties,for example,given a molecular structure predict its electronic *** is achieved with first principles calculations and more recently through machine learning approaches,since the former is computation-intensive and not practical for high-throughput *** for the right material for any given application,though follows an inverse path—the desired properties are given and the task is to find the right *** we present a deep learning inverse prediction framework,Structure Learning for Attributedriven Materials Design Using Novel Conditional Sampling(SLAMDUNCS),for efficient and accurate prediction of molecules exhibiting target *** apply this framework to the computational design of organic molecules for three applications,organic semiconductors for thin-film transistors,small organic acceptors for solar cells and electrolyte additives with high redox *** method is general enough to be extended to inorganic compounds and represents an important step in deep learning based completely automated materials discovery.