docs(04-machine-learning): Add decision boundary visualization code snippet #8

🎯 Goal

Add a hands-on code snippet in Module 4 (04-machine-learning/README.md) that plots and compares the Decision Boundaries of Logistic Regression, Decision Trees, and Random Forests on a 2D synthetic dataset.

📌 Motivation

Students often find mathematical classification equations abstract until they visually see how a linear model creates a straight line decision boundary, whereas a Decision Tree produces orthogonal rectangular splits, and a Random Forest creates a smooth, non-linear contour.

📋 Scope and Requirements

1. Target File: 04-machine-learning/README.md.
2. Implementation Details:
   • Generate a 2D dataset using sklearn.datasets.make_moons or make_blobs.
   • Fit 3 models:
     1. LogisticRegression (Linear boundary)
     2. DecisionTreeClassifier(max_depth=4) (Axis-aligned step boundary)
     3. RandomForestClassifier(n_estimators=50) (Ensemble smoothed boundary)
   • Use matplotlib and numpy.meshgrid (or sklearn.inspection.DecisionBoundaryDisplay) to create a clean side-by-side 1x3 subplot figure.
   • Include clear explanatory commentary on bias-variance tradeoffs observed in the plots.

🏷️ Good First Issue

Great visualization task for students learning Scikit-Learn and Matplotlib! Comment below to claim.