Mathematical Foundations of Machine Learning
A theoretical course focused exclusively on the mathematical principles of modern Machine Learning. This is not a course on ML programming or implementation.
Teaching
Teaching & Outreach
I regularly design and teach short courses and workshops on Python, scientific computing, and the mathematical foundations of machine learning, often combining formal derivations with live coding.
Short courses
PET.py Project (pt-br)
This project presents solutions to famous physics problems using knowledge of Computational Physics and the Python programming language.
A Brief Introduction to Machine Learning (pt-br)
A minicourse covering supervised and unsupervised learning, tensor computation, and dimensionality reduction, with emphasis on conceptual understanding and practical implementation in Python.
OlimPET Project (pt-br)
A project that aims to present physical and mathematical tools to assist in both understanding physical concepts and solving physics problems at the Olympic level in high school.
Introduction to Python for Chemical Engineering (pt-br)
Introductory Python course focused on scientific computing, including NumPy, Pandas, Matplotlib, SciPy and basic data analysis workflows.
Educational repositories
Many of my teaching materials are openly available on GitHub:
- Math-ML_Minicouse – noteboooks and exercises for the theoretical ML minicourse.
- PET.py – computational physics notebooks for topics such as astronomy, fluids, quantum and dynamical systems.
- Intro_ML – notebooks and exercises for the ML minicourse.
- Intro-Python_Eng-Quim – Python course tailored for Chemical Engineering students.