A Universal 3D Voxel Descriptor for Solid-State Material Informatics with Deep Convolutional Neural Networks
Abstract Material informatics (MI) is a promising approach to liberate us from the time-consuming Edisonian (trial and error) process for material discoveries, driven by machine-learning algorithms. Several descriptors, which are encoded material features to feed computers, were proposed in the last...
Main Authors: | Seiji Kajita, Nobuko Ohba, Ryosuke Jinnouchi, Ryoji Asahi |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2017-12-01
|
Series: | Scientific Reports |
Online Access: | https://doi.org/10.1038/s41598-017-17299-w |
Similar Items
-
Identifying superionic conductors by materials informatics and high-throughput synthesis
by: Masato Matsubara, et al.
Published: (2020-02-01) -
First-principles prediction of high oxygen-ion conductivity in trilanthanide gallates Ln3GaO6
by: Joohwi Lee, et al.
Published: (2019-12-01) -
Multi Voxel Descriptor for 3D Texture Retrieval
by: Hero Yudo Martono
Published: (2016-08-01) -
Multi Voxel Descriptor for 3D Texture Retrieval
by: Hero Yudo Martono
Published: (2016-08-01) -
A Voxelized Fractal Descriptor for 3D Object Recognition
by: Jose Francisco Domenech, et al.
Published: (2020-01-01)