supervised-learning

This repository provides a comprehensive guide to supervised machine learning, starting with foundational mathematics such as derivatives, probability, and logarithms. It uses a step-by-step approach to derive mathematical concepts before transitioning to modern tools. Key educational components include: - Logistic Regression: Theory and from-scratch implementation using the Wisconsin Breast Cancer dataset, alongside a production-grade PyTorch implementation. - Decision Trees: Theoretical deep dives with from-scratch implementations, and practical applications for predicting London housing prices using Scikit-learn, Random Forests, and XGBoost. - ATLAS (Automated Tree Learning Analysis System): A system for feature engineering and model comparison. - Datasets: Integration of the Wisconsin Breast Cancer and London Housing Prices datasets for classification and regression tasks. The material is delivered via Jupyter notebooks compatible with Google Colab for browser-based execution.