Classifying handedness in chiral nanomaterials using label error robust deep learning  

作　　者：C.K.Groschner Alexander J.Pattison Assaf Ben-Moshe A.Paul Alivisatos Wolfgang Theis M.C.Scott 

机构地区：[1]Department of Materials Science and Engineering,UC Berkeley,Berkeley,CA,USA [2]School of Physics and Astronomy,University of Birmingham,Birmingham,UK [3]Department of Chemistry,University of California,Berkeley,Berkeley,CA,USA [4]Materials Sciences Division,Lawrence Berkeley National Laboratory,Berkeley,CA,USA [5]Molecular Foundry,Lawrence Berkeley National Laboratory,Berkeley,Berkeley,CA,USA

出　　处：《npj Computational Materials》2022年第1期1417-1423,共7页计算材料学（英文）

基　　金：Work at the Molecular Foundry was supported by the Office of Science,Office of Basic Energy Sciences,of the US Department of Energy under Contract No.DE-AC02-05CH11231;This material is based upon work supported by the National Science Foundation Graduate Research Fellowship under Grant No.DGE-1752814;This work was also supported by National Science Foundation STROBE grant DMR-1548924。

摘　　要：High-throughput scanning electron microscopy(SEM)coupled with classification using neural networks is an ideal method to determine the morphological handedness of large populations of chiral nanoparticles.Automated labeling removes the time-consuming manual labeling of training data,but introduces label error,and subsequently classification error in the trained neural network.Here,we evaluate methods to minimize classification error when training from automated labels of SEM datasets of chiral Tellurium nanoparticles.Using the mirror relationship between images of opposite handed particles,we artificially create populations of varying label error.We analyze the impact of label error rate and training method on the classification error of neural networks on an ideal dataset and on a practical dataset.Of the three training methods considered,we find that a pretraining approach yields the most accurate results across label error rates on ideal datasets,where size and other morphological variables are held constant,but that a co-teaching approach performs the best in practical application.

关 键 词：ERROR CHIRAL REMOVE 

分 类 号：O62[理学—有机化学]