Learning Resources

Here you can find learning resources for programming languages, notebook tools, data handling, and machine learning. Resources listed are associated with non-commercial projects and institutions. Happy learning!

Programming Languages:

• Python:
  • Software Carpentry: Python
  • Software Carpentry: Plotting and Programming in Python
• R:
  • Software Carpentry: Programming with R
  • Software Carpentry: R for Reproducible Scientific Analysis
• Julia:
  • List of Tutorials
    

Software Libraries:

• Python:
  • Scikit-Learn. Library for machine learning and data analysis.
  • Scikit-Image. Library for image and video data analysis, also known as computer vision.
    

Notebook Tools:

• Jupyter Notebooks
• Pluto Notebooks
  

Data Publishing:

• Materials Data Facility
• Materials Data Curation System
  

Code handling:

• Git
  

Machine Learning:

• Reading materials:
  • Introduction to Statistical Learning. This book is often used as an undergraduate level textbook. You can find video lectures on the website as well.
  • Elements of Statistical Learning. This book is often used as a graduate level textbook.
  • Machine Learning in Materials Science: Recent Progress And Emerging Applications 2016. The first half is an intro to machine learning and the second half is a review of materials applications (2016).
• Bootcamps:
  • The annual Machine Learning for Materials Research Bootcamp and Workshop
• Courses:
  • Introduction to Statistical Learning. The book is listed above. This course is taught in R.
  • Practical Deep Learning for Coders
  • OpenDataScience Open Machine Learning Course. Provides Docker images for all software needed.
  • DataCamp. Collection of short courses - one per general topic.

NIST disclaimer: Certain commercial equipment, instruments, or materials are identified on this website. Such identification is not intended to imply recommendation or endorsement by the National Institute of Standards and Technology, nor is it intended to imply that the materials or equipment identified are necessarily the best available for the purpose.