Resources

• For questions after the workshop:

  • If you have questions about the analysis of the results or the statistics behind machine learning models, you can reach out to PSTAT’s DataLab
  • For questions about your project or specific questions on your code, you can ask our Carpentry @ UCSB #code_help Slack channel or email the Library’s DREAM Lab dreamlab@library.ucsb.edu.

• Depending on the task of your project, you don’t have to spend time training ML models from scratch! If your project involves text, images, or audio, you’ll probably find a model ready to be used on Hugging Face

• For continued self-paced learning, we recommend:

  • This lesson is part 1 of 4 from a curriculum on The Carpentries Incubator. The other lessons are
    • Introduction to Tree Models in Python (Lesson materials)
    • Introduction to artificial neural networks in Python (Lesson materials)
    • Responsible machine learning in Python (Lesson materials)
  • Google’s Intro to ML concepts and Crash Course

• Online asynchronous courses we’ve enjoyed and you can audit for free:

  • StanfordOnline: Statistical Learning with R
  • MITx: Machine Learning with Python: from Linear Models to Deep Learning

• Other Python resources:

  • The Hitchhiker’s Guide to Python
  • Scalable and Computationally Reproducible Approaches to Arctic Research

Glossary

---

FIXME