Introductory machine learning and deep learning lectures with hands-on practice. Includes a visual presentation of artificial neural networks created in Manim in collaboration with Ziad Kheil (doing remarkable work). The animation is available here | 2022 - 2025

Machine Learning Foundations

• Core supervised models - linear/logistic regression, SVM, trees, ensembles
• Unsupervised techniques - clustering, dimensionality reduction
• Model evaluation, validation, metrics

Optimization and Training Principles

• Loss functions and gradient-based optimization
• Overfitting, underfitting, and generalization
• Practical training workflows and debugging

Deep Learning

• Fully Connected Neural networks
• Backpropagation principles
• Convolutional Neural Networks