Classical ML

[!NOTE] This module covers the foundational “Classical” Machine Learning algorithms that power many real-world tabular data applications. We will explore tree-based models, moving from individual Decision Trees to powerful ensembles like Random Forests and Gradient Boosting Machines, focusing on intuition, mathematical rigor, and practical implementation.

Module Contents

1. Decision Trees

Understand how simple, interpretable splits can model complex non-linear relationships. We explore Information Gain, Gini Impurity, and how to build trees from scratch.

2. Random Forests

Learn how combining multiple weak learners creates a robust predictor. We dive into Bagging (Bootstrap Aggregating), feature randomness, and reducing variance without increasing bias.

3. Gradient Boosting

Discover the power of sequential learning, where each new tree corrects the errors of its predecessors. We unpack the math behind fitting residuals and why algorithms like XGBoost dominate tabular data competitions.

99. Module Review

Review key concepts with interactive flashcards, a comprehensive cheat sheet, and a quick revision guide to solidify your understanding of Classical ML.

Module Chapters