This course introduces the main concepts and techniques in machine learning (ML) with specific applications in several branches of physics.

    1.  Introduction. What is Machine Learning (ML) and what can we learn from ML?. Applications of machine learning in physics: After all we’ve been doing ML already.
    2.  Revisiting ML methods familiar to physicists: Linear models in regression and classification (logistic regression).
    3.  Introduction to other ML methods not usually covered in a physics degree. Support vector machines, Decision trees and ensemble models, KNN, Bayesian ML (if time allows!).
    4.  Hands-on: Introduction to python as a tool to do ML. Essential libraries. Implementation of a ML model in Python.
    5.  Assessing the model: Cross-validation, testing and optimization.
    6.  Big data and deep learning: Artificial intelligence. Introduction to some standard deep learning concepts and techniques.
    7. Convolutional neuronal networks for pattern recognition. Summary of other architectures.
    8. Unsupervised learning: Meaning and methods. (If time allows)
    9.  Proposal of projects.  
    10. Applications of ML in photonics.
    11.  Applications of ML in condensed matter physics.
    12.  Applications of ML in materials engineering and soft matter.
    13.  Summary. What did we learn? More literature, state of the art.