Tier 2 · Classical ML Prerequisite: AI & ML Foundations (Tier 1)

Classical Machine Learning

The algorithms that power most real-world production ML — fraud detection, recommendation, forecasting, segmentation. Before deep learning, these run the world. Learn them deeply, not just API calls.

10

Modules

41

Lessons

6–8

Weeks

Free

Always

Start Learning → All Courses

📋

Prerequisites: Tier 1 — AI & ML Foundations (linear regression, logistic regression, train/test split, NumPy, Pandas) or equivalent. You should be comfortable writing Python and running scikit-learn models before starting here.

Tools used:

🐍 Python 3.10+ ⚙️ scikit-learn 📊 Pandas 🔢 NumPy 📈 Matplotlib ⚡ XGBoost 💾 joblib

Course Contents

10 Modules

Each module builds on the last. Capstone at the end wraps everything into one end-to-end project.

Phase A — The sklearn Toolkit & Core Algorithms

MODULE 014 lessons

The scikit-learn Workflow

Estimators, transformers, Pipelines, ColumnTransformer, saving models with joblib

⏱ 2hFoundation→

MODULE 025 lessons

Decision Trees & Ensembles

Gini/entropy splits, pruning, Random Forests, XGBoost, feature importance

⏱ 3.5hSupervised→

MODULE 034 lessons

Support Vector Machines

Margin maximization, the kernel trick, SVC and SVR, when to choose SVMs

⏱ 2.5hSupervised→

Phase B — Unsupervised Learning & Data Preparation

MODULE 045 lessons

Unsupervised: Clustering

K-Means, elbow method, silhouette score, hierarchical clustering, DBSCAN

⏱ 3hUnsupervised→

MODULE 054 lessons

Dimensionality Reduction

The curse of dimensionality, PCA, t-SNE, UMAP, when to reduce before modeling

⏱ 2.5hUnsupervised→

MODULE 065 lessons

Feature Engineering

Creating features, encoding categoricals, text & date features, feature selection

⏱ 3hPreparation→

Phase C — Advanced Topics & Specializations

MODULE 074 lessons

Model Evaluation & Tuning

Grid search, random search, learning curves, handling imbalanced datasets

⏱ 3hOptimization→

MODULE 085 lessons

Time Series Basics

Trend & seasonality, ARIMA, correct train/test splits, sales forecasting project

⏱ 3hSpecialized→

MODULE 094 lessons

Recommendation Systems

Collaborative filtering, content-based, hybrid approaches, movie recommender project

⏱ 2.5hSpecialized→

Phase D — Capstone

MODULE 10Capstone

End-to-End ML Project

Problem framing, full pipeline (EDA → features → model → eval), Flask/FastAPI deployment, presenting results

⏱ 4hProject→

TIER 312 modules

Deep Learning & Neural Networks

Neural networks from scratch, PyTorch, CNNs, RNNs, Transformers, generative models and RL

⏱ 40h+Advanced→