Using Weakly Supervised Deep Learning to Classify and Segment Single-Molecule Break-Junction Conductance Traces
Citation:
Lin, D., Zhao, Z., Pan, H., Li, S., Wang, Y., Wang, D., Sanvito, S., Hou, S., Using Weakly Supervised Deep Learning to Classify and Segment Single-Molecule Break-Junction Conductance Traces, ChemPhysChem, 2021 Oct 14;22(20):2107-2114Download Item:
Abstract:
In order to design molecular electronic devices with high performance and stability, it is crucial to understand their structure-to-property relationships. Single-molecule break junction measurements yield a large number of conductance-distance traces, which are inherently highly stochastic. Here we propose a weakly supervised deep learning algorithm to classify and segment these conductance traces, a method that is mainly based on transfer learning with the pretrain-finetune technique. By exploiting the powerful feature extraction capabilities of the pretrained VGG-16 network, our convolutional neural network model not only achieves high accuracy in the classification of the conductance traces, but also segments precisely the conductance plateau from an entire trace with very few manually labeled traces. Thus, we can produce a more reliable estimation of the junction conductance and quantify the junction stability. These findings show that our model has achieved a better accuracy-to-manpower efficiency balance, opening up the possibility of using weakly supervised deep learning approaches in the studies of single-molecule junctions.
Author's Homepage:
http://people.tcd.ie/sanvitosDescription:
PUBLISHED
Author: Sanvito, Stefano
Type of material:
Journal ArticleCollections
Series/Report no:
ChemPhysChem;22;
20;
Availability:
Full text availableKeywords:
Transfer learning, Single-molecule junction, Pretrain-finetune, Conductance-distance trace, Deep learningDOI:
http://dx.doi.org/10.1002/cphc.202100414Metadata
Show full item recordLicences: