J. Hruska and I created this tutorial as an introduction to processing spectroscopic data in Python. It covers everything from loading the data, exploration and visualization, preprocessing, and feature extraction, up to classification — using PCA, t-SNE, random forest, SVM, and MLP. It's used for the DS114 (Laser-Induced Breakdown Spectroscopy) Ph.D. course at the CEITEC PhD School.
2–3 guest lectures covering an introduction to Artificial Neural Networks (ANN) and ANN applications in physics. The last lecture covers practical implementation in Python (topics selected on the go; past years included backprop without libraries, object-oriented ANN code from scratch, a Keras classifier, and a basic data-processing pipeline for spectroscopic data). Based on A high-bias, low-variance introduction to Machine Learning for physicists and Machine Learning for Physicists (F. Marquardt).