Work

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

Year: 2020

Type: 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.

Source: Optics in the Life Sciences

DOI: 10.1364/translational.2020.jth2a.28

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

Institutions: Lawrence Berkeley National Laboratory, National Energy Research Scientific Computing Center, National Laboratory of the Rockies, Northeastern University

Language: English

Topic: Advanced X-ray Imaging Techniques

Subfield: Radiation

Field: Physics and Astronomy

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W3016854908

FWCI: 1.85

Cites: 3

Cited by: 4

Related to: 10