This repository contains the public material for my Machine Learning course: lecture notes with code examples and lab works.
I have tried to write them in such a way that they should be accessible to anyone wanting to learn the subject, regardless of whether you are one of my students or not.
Supervised Learning is a subset of Machine Learning in which expected results are fed into the system alongside training data.
- Principles of supervised learning
- End-to-end project workflow
- Assessing classification performance
- Learning via Gradient Descent
- Lab: Predict heart disease
- 🚧 Linear Regression
- 🚧 Decision Trees & Random Forests
- ... (more to come)
Deep Learning is a subset of Machine Learning based on the usage of large neural networks trained on vast amounts of data.
- Feedforward Neural Networks
- Lab: Introduction to PyTorch
- Lab: Classify 2D data with a neural network
- Convolutional Neural Networks
- ... (more to come)
Reinforcement Learning is a subset of Machine Learning concerned with the maximization of rewards in a dynamic environment.
- 🚧 Introduction to Reinforcement Learning
- ... (more to come)
git clone https://github.com/bpesquet/mlcourse.git
cd mlcourse
python {path to Python code file}
This project is built with the following software:
- Poetry for dependency management;
- Black for code formatting;
- Pylint to detect mistakes in the code;
- pytest for testing the code;
- Marp for showcasing notes as slideshows during lectures.
# Reformat all Python files
black .
# Check the code for mistakes
pylint lectures
# Run all code examples as unit tests
# The -s flag prints code output
pytest [-s] .
Creative Commons for textual content and MIT for code.
Copyright © 2024-present Baptiste Pesquet.