A Molecular-MNIST Dataset for Machine Learning Study on Diffraction Imaging and Microscopy: Paper No. JTh2A.28

Yan Zhang; Steve Farrell; Michael Crowley; Lee Makowski; Jack Deslippe

doi:10.1364/TRANSLATIONAL.2020.JTh2A.28

A Molecular-MNIST Dataset for Machine Learning Study on Diffraction Imaging and Microscopy: Paper No. JTh2A.28

Yan Zhang
, Steve Farrell
, Michael Crowley
, Lee Makowski
, Jack Deslippe

Renewable Resources and Enabling Sciences Center

Lawrence Berkeley National Laboratory
Northeastern University

Research output: Contribution to conference › Paper

Abstract

An image dataset of 10 different size molecules, where each molecule has 2,000 structural variants, is generated from the 2D cross-sectional projection of Molecular Dynamics trajectories. The purpose of this dataset is to provide a benchmark dataset for the increasing need of machine learning, deep learning and image processing on the study of scattering, imaging and microscopy.

Original language	American English
Number of pages	2
DOIs	https://doi.org/10.1364/TRANSLATIONAL.2020.JTh2A.28
State	Published - 2020
Event	Biophotonics Congress: Biomedical Optics 2020 (Translational, Microscopy, OCT, OTS, BRAIN), part of Microscopy Histopathology and Analytics 2020 - Washington, D.C. Duration: 20 Apr 2020 → 23 Apr 2020

Conference

Conference	Biophotonics Congress: Biomedical Optics 2020 (Translational, Microscopy, OCT, OTS, BRAIN), part of Microscopy Histopathology and Analytics 2020
City	Washington, D.C.
Period	20/04/20 → 23/04/20

NLR Publication Number

NREL/CP-2800-78074

Keywords

deep learning
image processing
molecular dynamics
molecules
photonics

Access to Document

10.1364/TRANSLATIONAL.2020.JTh2A.28

Cite this

Zhang, Y., Farrell, S., Crowley, M., Makowski, L., & Deslippe, J. (2020). A Molecular-MNIST Dataset for Machine Learning Study on Diffraction Imaging and Microscopy: Paper No. JTh2A.28. Paper presented at Biophotonics Congress: Biomedical Optics 2020 (Translational, Microscopy, OCT, OTS, BRAIN), part of Microscopy Histopathology and Analytics 2020, Washington, D.C.. https://doi.org/10.1364/TRANSLATIONAL.2020.JTh2A.28

@conference{97844aef041448e4807aab7599b55f19,

title = "A Molecular-MNIST Dataset for Machine Learning Study on Diffraction Imaging and Microscopy: Paper No. JTh2A.28",

abstract = "An image dataset of 10 different size molecules, where each molecule has 2,000 structural variants, is generated from the 2D cross-sectional projection of Molecular Dynamics trajectories. The purpose of this dataset is to provide a benchmark dataset for the increasing need of machine learning, deep learning and image processing on the study of scattering, imaging and microscopy.",

keywords = "deep learning, image processing, molecular dynamics, molecules, photonics",

author = "Yan Zhang and Steve Farrell and Michael Crowley and Lee Makowski and Jack Deslippe",

year = "2020",

doi = "10.1364/TRANSLATIONAL.2020.JTh2A.28",

language = "American English",

note = "Biophotonics Congress: Biomedical Optics 2020 (Translational, Microscopy, OCT, OTS, BRAIN), part of Microscopy Histopathology and Analytics 2020 ; Conference date: 20-04-2020 Through 23-04-2020",

}

Zhang, Y, Farrell, S, Crowley, M, Makowski, L & Deslippe, J 2020, 'A Molecular-MNIST Dataset for Machine Learning Study on Diffraction Imaging and Microscopy: Paper No. JTh2A.28', Paper presented at Biophotonics Congress: Biomedical Optics 2020 (Translational, Microscopy, OCT, OTS, BRAIN), part of Microscopy Histopathology and Analytics 2020, Washington, D.C., 20/04/20 - 23/04/20. https://doi.org/10.1364/TRANSLATIONAL.2020.JTh2A.28

A Molecular-MNIST Dataset for Machine Learning Study on Diffraction Imaging and Microscopy: Paper No. JTh2A.28. / Zhang, Yan; Farrell, Steve; Crowley, Michael et al.
2020. Paper presented at Biophotonics Congress: Biomedical Optics 2020 (Translational, Microscopy, OCT, OTS, BRAIN), part of Microscopy Histopathology and Analytics 2020, Washington, D.C..

Research output: Contribution to conference › Paper

TY - CONF

T1 - A Molecular-MNIST Dataset for Machine Learning Study on Diffraction Imaging and Microscopy

T2 - Biophotonics Congress: Biomedical Optics 2020 (Translational, Microscopy, OCT, OTS, BRAIN), part of Microscopy Histopathology and Analytics 2020

AU - Zhang, Yan

AU - Farrell, Steve

AU - Crowley, Michael

AU - Makowski, Lee

AU - Deslippe, Jack

PY - 2020

Y1 - 2020

N2 - An image dataset of 10 different size molecules, where each molecule has 2,000 structural variants, is generated from the 2D cross-sectional projection of Molecular Dynamics trajectories. The purpose of this dataset is to provide a benchmark dataset for the increasing need of machine learning, deep learning and image processing on the study of scattering, imaging and microscopy.

AB - An image dataset of 10 different size molecules, where each molecule has 2,000 structural variants, is generated from the 2D cross-sectional projection of Molecular Dynamics trajectories. The purpose of this dataset is to provide a benchmark dataset for the increasing need of machine learning, deep learning and image processing on the study of scattering, imaging and microscopy.

KW - deep learning

KW - image processing

KW - molecular dynamics

KW - molecules

KW - photonics

U2 - 10.1364/TRANSLATIONAL.2020.JTh2A.28

DO - 10.1364/TRANSLATIONAL.2020.JTh2A.28

M3 - Paper

Y2 - 20 April 2020 through 23 April 2020

ER -

Zhang Y, Farrell S, Crowley M, Makowski L, Deslippe J. A Molecular-MNIST Dataset for Machine Learning Study on Diffraction Imaging and Microscopy: Paper No. JTh2A.28. 2020. Paper presented at Biophotonics Congress: Biomedical Optics 2020 (Translational, Microscopy, OCT, OTS, BRAIN), part of Microscopy Histopathology and Analytics 2020, Washington, D.C.. doi: 10.1364/TRANSLATIONAL.2020.JTh2A.28

A Molecular-MNIST Dataset for Machine Learning Study on Diffraction Imaging and Microscopy: Paper No. JTh2A.28

Abstract

Conference

NLR Publication Number

Keywords

Access to Document

Fingerprint

Cite this