Skip to content

Training materials on AI/ML in Heliophysics

License

Notifications You must be signed in to change notification settings

AyrisA/AIML_Class

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Center for HelioAnalytics

Machine Learning Tutorial

Brought to you by:

Center for Helioanalytics logoNational Center for Climate Studies logoHelioCloud.org logo

This series of tutorials is part of the 2024 Python in Heliophysics Summer School held May 20-24, 2024.

Machine Learning Tutorial Course Materials

Session Lecture Topic Link Timing
Session 1 Introduction
Session 1A What is Machine Learning? Link 15 min.
Session 1B How does Machine Learning work? Link 15 min.
Session 2 Examples: ML Models
Session 2A Clustering Link 20 min.
Session 2B Decision Boundary Link 20 min.
Session 2C Decision Boundary using TensorFlow Link 20 min.
Session 2D Classifier Link 20 min.
Session 3 Data Science Workflow Link 15 min.

Use and Dependencies

These materials were developed for the summer school students, but are intended to function as stand-alone lessons freely to be used by anyone.

The lessons use the following packages: numpy, pandas, matplotlib, and tensorflow (keras).

Acknowledgments

These course materials were developed by the Center for HelioAnalytics (CfHA) with the support of funding from NASA. We request that any subsequent use acknowledge CfHA.

The course materials were derived in part from the 2022 NASA EPSCOR Hack Week hosted by West Virginia University.

In adddition to the Center for HelioAnalytics team members, we want to acknowledge the following authors for their major contributions to these course materials:
Evana Gizzi, Ph.D., AI Researcher NASA GSFC
Richard Licata, Ph.D., Data Scientist, CACI International

Additional Resources

Books and texts

Online articles

About

Training materials on AI/ML in Heliophysics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Jupyter Notebook 100.0%