Recently, Machine-Learning (ML) has become very popular in the field of Geosciences as datasets are becoming increasingly large. Thus, having a grasp of what this is all about can prove to be a useful skill for your future career. To this end, the course will serve as in introduction to the basic concepts of ML. You will learn about the fundamental concepts of supervised learning as well as some overview on more advanced topics such as deep learning. The course will focus on some specific algorithms (bayesian classification, support vector machine, random forests, clustering, neural networks and autoencoders). Each method will be accompanied by practicals applied to geophysical data.
 

At the end of the course, the student should have a general sense of what is Machine Learning along with theoretical and practical knowledge about several machine learning algorithms.
 

1. Goodfellow et al. (2016). Deep Learning. MIT Press, url:hWp://www.deeplearningbook.org
2. VanderPlas (2016). Python Data Science Handbook. O’Reilly Media, Inc. url:hWps://jakevdp.github.io/ PythonDataScienceHandbook/
3. Murphy (2012). Machine Learning: A Probabilistic Perspective. MIT Press, Cambridge, MassachuseWs.
4. Richert and Coelho (2013). Building Machine Learning Systems with Python. Packt Publishing Ltd, Birmingham, UK.

 

Students should have a strong background in Geosciences, Mathematics (optimization, statistics, calculus) as well as a moderate level in coding using Python language.