Skip to main content
U.S. flag

An official website of the United States government

This site is currently in beta, and your feedback is helping shape its ongoing development.

Return to search results

Theory aware Machine Learning (TaML)

Published by National Institute of Standards and Technology | National Institute of Standards and Technology | Metadata Last Checked: August 02, 2025 | Last Modified: 2022-05-06 00:00:00
A code repository and accompanying data for incorporating imperfect theory into machine learning for improved prediction and explainability. Specifically, it focuses on the case study of the dimensions of a polymer chain in different solvent qualities. Jupyter Notebooks for quickly testing concepts and reproducing figures, as well as source code that computes the mean squared error as a function of dataset size for various machine learning models are included.For additional details on the data, please refer to the README.md associated with the data. For additional details on the code, please refer to the README.md provided with the code repository (GitHub Repo for Theory aware Machine Learning). For additional details on the methodology, see Debra J. Audus, Austin McDannald, and Brian DeCost, "Leveraging Theory for Enhanced Machine Learning" *ACS Macro Letters* **2022** *11* (9), 1117-1122 DOI: [10.1021/acsmacrolett.2c00369](https://doi.org/10.1021/acsmacrolett.2c00369).

Resources

87 resources available

Find Related Datasets

Click any tag below to search for similar datasets

Complete Metadata
@type dcat:Dataset
accessLevel public
bureauCode 
                                            [
  "006:55"
]
contactPoint 
                                            {
  "fn": "Debra Audus",
  "hasEmail": "mailto:debra.audus@nist.gov"
}
description A code repository and accompanying data for incorporating imperfect theory into machine learning for improved prediction and explainability. Specifically, it focuses on the case study of the dimensions of a polymer chain in different solvent qualities. Jupyter Notebooks for quickly testing concepts and reproducing figures, as well as source code that computes the mean squared error as a function of dataset size for various machine learning models are included.For additional details on the data, please refer to the README.md associated with the data. For additional details on the code, please refer to the README.md provided with the code repository (GitHub Repo for Theory aware Machine Learning). For additional details on the methodology, see Debra J. Audus, Austin McDannald, and Brian DeCost, "Leveraging Theory for Enhanced Machine Learning" *ACS Macro Letters* **2022** *11* (9), 1117-1122 DOI: [10.1021/acsmacrolett.2c00369](https://doi.org/10.1021/acsmacrolett.2c00369).
distribution 
                                            [
  {
    "title": "GitHub Repo for Theory aware Machine Learning (TaML)",
    "format": "HTML",
    "accessURL": "https://github.com/usnistgov/TaML"
  },
  {
    "title": "README",
    "format": "text",
    "mediaType": "text/plain",
    "description": "README file for Theory aware Machine Learning (TaML)",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/README.md"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/README.md.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_difference.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_difference.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_direct.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_direct.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_fixedprior.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_fixedprior.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_latentvariable.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_latentvariable.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_linearprior.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_linearprior.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_difference.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_difference.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_direct.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_direct.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_fixedprior.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_fixedprior.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_latentvariable.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_latentvariable.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_linearprior.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_linearprior.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_parameterization.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_parameterization.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_quotient.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_out_quotient.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_parameterization.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_parameterization.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_quotient.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/hetero_quotient.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_difference.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_difference.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_direct.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_direct.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_fixedprior.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_fixedprior.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_latentvariable.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_latentvariable.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_linearprior.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_linearprior.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_difference.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_difference.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_direct.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_direct.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_fixedprior.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_fixedprior.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_latentvariable.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_latentvariable.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_linearprior.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_linearprior.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_parameterization.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_parameterization.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_quotient.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_out_quotient.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_parameterization.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_parameterization.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_quotient.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/homo_quotient.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/out_theory.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/out_theory.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_difference_1000_None.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_difference_1000_None.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_direct_1000_None.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_direct_1000_None.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_latentvariable_1000_None.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_latentvariable_1000_None.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_multitask_1000_None.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_multitask_1000_None.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_difference_1000_None.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_difference_1000_None.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_direct_1000_None.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_direct_1000_None.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_latentvariable_1000_None.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_latentvariable_1000_None.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_multitask_1000_None.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_multitask_1000_None.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_quotient_1000_None.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_out_quotient_1000_None.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_quotient_1000_None.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/rf_quotient_1000_None.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/theory.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/mse/theory.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/testtrain/rgmaindata.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/testtrain/rgmaindata.csv.sha256"
  },
  {
    "mediaType": "text/csv",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/testtrain/rgoutlierdata.csv"
  },
  {
    "mediaType": "text/plain",
    "downloadURL": "https://data.nist.gov/od/ds/ark:/88434/mds2-2637/testtrain/rgoutlierdata.csv.sha256"
  }
]
identifier ark:/88434/mds2-2637
keyword 
                                            [
  "machine learning",
  "polymers",
  "theory",
  "transfer learning"
]
landingPage https://data.nist.gov/od/id/mds2-2637
language 
                                            [
  "en"
]
license https://www.nist.gov/open/license
modified 2022-05-06 00:00:00
programCode 
                                            [
  "006:045"
]
publisher 
                                            {
  "name": "National Institute of Standards and Technology",
  "@type": "org:Organization"
}
references 
                                            [
  "https://dx.doi.org/10.1021/acsmacrolett.2c00369"
]
theme 
                                            [
  "Information Technology:Data and informatics",
  "Materials:Modeling and computational material science",
  "Materials:Polymers",
  "Mathematics and Statistics:Uncertainty quantification"
]
title Theory aware Machine Learning (TaML)

data.gov

An official website of the GSA's Technology Transformation Services

Looking for U.S. government information and services?
Visit USA.gov