The role of convolutional neural networks in scanning probe microscopy: a review

Beilstein Journal of Nanotechnology

article

Ido Azuri¹  Irit Rosenhek-Goldian²  Neta Regev-Rudzki³  Georg Fantner⁴  Sidney R. Cohen² 

[1] Weizmann Institute of Science, Department of Life Sciences Core Facilities;Weizmann Institute of Science, Department of Chemical Research Support;Weizmann Institute of Science, Department of Biomolecular Sciences;École Polytechnique Fédérale de Lausanne, Laboratory for Bio- and Nano-Instrumentation

关键词: atomic force microscopy (AFM);    deep learning;    machine learning;    neural networks;    scanning probe microscopy (SPM);   

DOI  :  10.3762/bjnano.12.66

学科分类：环境监测和分析

来源: Beilstein - Institut zur Foerderung der Chemischen Wissenschaften

【 摘 要 】

Progress in computing capabilities has enhanced science in many ways. In recent years, various branches of machine learning havebeen the key facilitators in forging new paths, ranging from categorizing big data to instrumental control, from materials designthrough image analysis. Deep learning has the ability to identify abstract characteristics embedded within a data set, subsequentlyusing that association to categorize, identify, and isolate subsets of the data. Scanning probe microscopy measures multimodal surface properties, combining morphology with electronic, mechanical, and other characteristics. In this review, we focus on a subsetof deep learning algorithms, that is, convolutional neural networks, and how it is transforming the acquisition and analysis of scanning probe data.

【 授权许可】

CC BY