Microstructure representation learning using Siamese networks

Obtaining a good statistical representation of material microstructures is crucial for establishing robust process–structure–property linkages and machine learning techniques can bridge this gap. One major difficulty in leveraging recent advances in deep learning for this purpose is the scarcity of...

Full description

Saved in:
Bibliographic Details
Published in:MRS communications 2020-12, Vol.10 (4), p.613-619
Main Authors: Sardeshmukh, Avadhut, Reddy, Sreedhar, Gautham, B.P., Bhattacharyya, Pushpak
Format: Article
Language:English
Subjects:
Biomaterials
Characterization and Evaluation of Materials
Classification
Datasets
Deep learning
Grain size
Machine learning
Materials Engineering
Materials Science
Methods
Microscopy
Microstructure
Nanotechnology
Neural networks
Polymer Sciences
Representations
Research Letters
Semantics
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Obtaining a good statistical representation of material microstructures is crucial for establishing robust process–structure–property linkages and machine learning techniques can bridge this gap. One major difficulty in leveraging recent advances in deep learning for this purpose is the scarcity of good quality data with enough metadata. In machine learning, similarity metric learning using Siamese networks has been used to deal with sparse data. Inspired by this, the authors propose a Siamese architecture to learn microstructure representations. The authors show that analysis tasks such as the classification of microstructures can be done more efficiently in the learned representation space.
ISSN:2159-6859
2159-6867
DOI:10.1557/mrc.2020.55