There are a lot(!) of free online resources available if you want to learn practical machine learning skills, workflows, and processes. The following are just a few of the highlights that I recommend, but there are many, many more that might work out better for you. Unlike my previous post — Recommended Books for Machine Learning — these are in no order.
An example generative AI image (Click to enlarge)
-
Scikit-Learn MOOC
This MOOC does not run all the time, but the resources are all online and free to use. Scikit-learn is a great package, and where most machine learners should start. -
Stat-Quest with Josh Starmer
This is not a course per se, but a collection of videos that explains machine learning methods and workflows. The 3Blue1Brown channel would be another option if you prefer the video format. I regularly watch stat quest videos when I need to refresh on a method or architecture. -
ECMWF MOOC Machine Learning in Weather & Climate
This is a brand new course that combines practical atmospheric data handling considerations with machine learning examples in Python. Fantastic content! -
Satellite Image Deep Learning
This is a great repository of satellite image deep learning projects on Github. It's a great place to find a project or code snippets that might help you with your own work. -
Google Developers Crash Course
This is a really well done, browser-based course that uses the tensorflow API. If you are just interested in deep learning, but not ready to write code, this is the place to start. -
Fast.ai course
This is a deep learning course with great Jupyter Notebook support.
Are there other courses or resources that you recommend for learning machine learning? Feel free to comment below or send me an email with your favorites!
Thomas Martin is an AI/ML Software Engineer at the Unidata Program Center. Have questions? Contact support-ml@unidata.ucar.edu or book an office hours meeting with Thomas on his Calendar.
