Welcome to the repository of the Machine Learning lecture given at the winter school of the Réseau Français de Chimie Théorique (RCTF) held from 17-28 January 2022. This repository includes the slides of the lecture about "Introduction to Supervised Machine Learning for Chemistry" and a jupyter notebook written in Python for the practical tutorial section.
http://www.chimie-theorique.cnrs.fr/spip.php?article994&lang=fr
-
Linear regression models
- Ordinary least-squares;
- Gradient descent;
- Ridge regression.
-
Non-linear regression models
- Polynomial feature map;
- The kernel trick;
- Kernel ridge regression.
The hands-on tutorial was designed to run in a jupyter notebook environment with
- python3 (tested with version 3.8.1)
The following libraries are requested for the tutorial:
-
Math and data processing libraries:
- pandas
- numpy
- scikit-learn
-
For visualization:
- seaborn
- matplotlib
- plotly
-
Specialized packages:
- mendeleev
The Jupyter notebook tutorial can be also executed in Google Colab.
- Liu, X., Meijer, G. & Pérez-Ríos, J., A data-driven approach to determine dipole moments of diatomic molecules. Phys. Chem. Chem. Phys., 22, 24191 (2020)
- Rupp, M., Machine Learning for Quantum Mechanics in a Nutshell. Int. J. Quantum Chem., 115, 1058 (2015)