You must login before you can run this tool.
Materials Simulation Toolkit for Machine Learning (MAST-ML) tutorial
Tutorial showing the many use cases for the MAST-ML package to build, evaluate and analyze machine learning models for materials applications.
Category
Published on
Abstract
Welcome to the Tutorial series for using the Materials Simulation Toolkit for Machine Learning (MAST-ML)!
MAST-ML is an open-source python package designed to broaden and accelerate the use of machine learning methods in materials science
Github: https://github.com/uw-cmg/MAST-ML
Paper Citation: https://doi.org/10.1016/j.commatsci.2020.109544
Tool Contents
Tutorial 1: Getting Started with MAST-ML
Tutorial 2: Data Import and Cleaning with MAST-ML
Tutorial 3: Feature Engineering with MAST-ML
Tutorial 4: Models and Data Splitting Tests with MAST-ML
Tutorial 5: Left out data, nested cross validation, and optimized models with MAST-ML
Tutorial 6: Model error analysis and uncertainty quantification with MAST-ML
Tutorial 7: Model predictions with calibrated error bars on new data, model hosting to Foundry/DLHub
Credits
University of Wisconsin-Madison Computational Materials Group
Publications
Jacobs, R., Mayeshiba, T., Afflerbach, B., Miles, L., Williams, M., Turner, M., Finkel, R., Morgan, D., "The Materials Simulation Toolkit for Machine Learning (MAST-ML): An automated open source toolkit to accelerate data-driven materials research", Computational Materials Science 175 (2020).
Cite this work
Researchers should cite this work as follows: