Correlator convolutional neural networks as an interpretable architecture for image-like quantum matter data
Physical principles underlying machine learning analysis of quantum gas microscopy data are not well understood. Here the authors develop a neural network based approach to classify image data in terms of multi-site correlation functions and reveal the role of fourth-order correlations in the Fermi-...
Main Authors: | , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Publishing Group
2021-06-01
|
Series: | Nature Communications |
Online Access: | https://doi.org/10.1038/s41467-021-23952-w |
id |
doaj-c5f988f964a14deb9630bb1251319555 |
---|---|
record_format |
Article |
spelling |
doaj-c5f988f964a14deb9630bb12513195552021-06-27T11:12:34ZengNature Publishing GroupNature Communications2041-17232021-06-011211710.1038/s41467-021-23952-wCorrelator convolutional neural networks as an interpretable architecture for image-like quantum matter dataCole Miles0Annabelle Bohrdt1Ruihan Wu2Christie Chiu3Muqing Xu4Geoffrey Ji5Markus Greiner6Kilian Q. Weinberger7Eugene Demler8Eun-Ah Kim9Department of Physics, Cornell UniversityDepartment of Physics, Harvard UniversityDepartment of Computer Science, Cornell UniversityDepartment of Physics, Harvard UniversityDepartment of Physics, Harvard UniversityDepartment of Physics, Harvard UniversityDepartment of Physics, Harvard UniversityDepartment of Computer Science, Cornell UniversityDepartment of Physics, Harvard UniversityDepartment of Physics, Cornell UniversityPhysical principles underlying machine learning analysis of quantum gas microscopy data are not well understood. Here the authors develop a neural network based approach to classify image data in terms of multi-site correlation functions and reveal the role of fourth-order correlations in the Fermi-Hubbard model.https://doi.org/10.1038/s41467-021-23952-w |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Cole Miles Annabelle Bohrdt Ruihan Wu Christie Chiu Muqing Xu Geoffrey Ji Markus Greiner Kilian Q. Weinberger Eugene Demler Eun-Ah Kim |
spellingShingle |
Cole Miles Annabelle Bohrdt Ruihan Wu Christie Chiu Muqing Xu Geoffrey Ji Markus Greiner Kilian Q. Weinberger Eugene Demler Eun-Ah Kim Correlator convolutional neural networks as an interpretable architecture for image-like quantum matter data Nature Communications |
author_facet |
Cole Miles Annabelle Bohrdt Ruihan Wu Christie Chiu Muqing Xu Geoffrey Ji Markus Greiner Kilian Q. Weinberger Eugene Demler Eun-Ah Kim |
author_sort |
Cole Miles |
title |
Correlator convolutional neural networks as an interpretable architecture for image-like quantum matter data |
title_short |
Correlator convolutional neural networks as an interpretable architecture for image-like quantum matter data |
title_full |
Correlator convolutional neural networks as an interpretable architecture for image-like quantum matter data |
title_fullStr |
Correlator convolutional neural networks as an interpretable architecture for image-like quantum matter data |
title_full_unstemmed |
Correlator convolutional neural networks as an interpretable architecture for image-like quantum matter data |
title_sort |
correlator convolutional neural networks as an interpretable architecture for image-like quantum matter data |
publisher |
Nature Publishing Group |
series |
Nature Communications |
issn |
2041-1723 |
publishDate |
2021-06-01 |
description |
Physical principles underlying machine learning analysis of quantum gas microscopy data are not well understood. Here the authors develop a neural network based approach to classify image data in terms of multi-site correlation functions and reveal the role of fourth-order correlations in the Fermi-Hubbard model. |
url |
https://doi.org/10.1038/s41467-021-23952-w |
work_keys_str_mv |
AT colemiles correlatorconvolutionalneuralnetworksasaninterpretablearchitectureforimagelikequantummatterdata AT annabellebohrdt correlatorconvolutionalneuralnetworksasaninterpretablearchitectureforimagelikequantummatterdata AT ruihanwu correlatorconvolutionalneuralnetworksasaninterpretablearchitectureforimagelikequantummatterdata AT christiechiu correlatorconvolutionalneuralnetworksasaninterpretablearchitectureforimagelikequantummatterdata AT muqingxu correlatorconvolutionalneuralnetworksasaninterpretablearchitectureforimagelikequantummatterdata AT geoffreyji correlatorconvolutionalneuralnetworksasaninterpretablearchitectureforimagelikequantummatterdata AT markusgreiner correlatorconvolutionalneuralnetworksasaninterpretablearchitectureforimagelikequantummatterdata AT kilianqweinberger correlatorconvolutionalneuralnetworksasaninterpretablearchitectureforimagelikequantummatterdata AT eugenedemler correlatorconvolutionalneuralnetworksasaninterpretablearchitectureforimagelikequantummatterdata AT eunahkim correlatorconvolutionalneuralnetworksasaninterpretablearchitectureforimagelikequantummatterdata |
_version_ |
1721358185081602048 |