/machine-learning

Open textbook: A practical introduction to machine learning in geophysics

Primary LanguageJupyter NotebookOtherNOASSERTION

A quick introduction to machine learning 2023 update

Author: Leonardo Uieda

This is a very brief hands-on introduction to machine learning. It will cover some of the common nomenclature, principles, and applications.

Binder

📓 • Jupyter Notebook

The tutorial is in the form of a Jupyter notebook (tutorial.ipynb). Here are some options for using it:

🧑🏿‍💻 • Learner profile

  • Is currently in their final year of a STEM undergraduate degree or early years of a postgraduate degree.
  • Has studies the basics of statistics, Python programming, and linear algebra.
  • Is interested in using machine learning in their projects or as a future career.

🧑‍🏫 • For instructors

The tutorial is designed to be taught as a 1-2 hour session with live-coding. To do so, create a copy of the notebook and delete all or most of the code cells (it's OK to leave some in to allow more time in the tutorial).

Type in the code as you explain what you're doing. This will help you control your pacing and avoid going too fast. It also opens up the opportunity for you to make mistakes and teach students how to identify and solve them.

Ideally, have them follow along on their own computers, typing in the code with you. Make sure you also share a copy of the pre-filled notebook with students so that they can choose to not type and listen at the same time.

⚖️ • License

The original material for this tutorial can be found at leouieda/ml-intro. Comments, corrections, and additions are welcome.

All Python source code is made available under the BSD 3-clause license. You can freely use and modify the code, without warranty, so long as you provide attribution to the authors.

Unless otherwise specified, all figures and Jupyter notebooks are available under the Creative Commons Attribution 4.0 License (CC-BY).

The full text of these licenses is provided in the LICENSE.txt file.