Course Curriculum

Your learning path consists of 9 main modules plus project work.

You’ll begin with Module 1 covering introduction and setup, then progress through Linear Regression (Module 2) with a car price prediction project.

Binary Classification (Module 3) introduces customer churn prediction, while Model Evaluation (Module 4) covers critical but challenging assessment concepts.

Model Deployment (Module 5) teaches FastAPI implementation, and Tree-Based Models (Module 6) explores loan default prediction.

Module 7 represents your Midterm Project—three weeks of independent work applying everything learned so far.

The advanced modules include Neural Networks and Deep Learning (Module 8) with PyTorch, Serverless Deployment (Module 9) using AWS Lambda and ONNX, and Kubernetes Deployment (Module 10).

Module 11 covers KServe but is optional and potentially outdated—focus your energy on Kubernetes instead.

Learning Philosophy

The course follows a project-first approach where theory is introduced as needed to solve real problems. This means you’ll learn by doing rather than studying abstract concepts first. The emphasis is practical over theoretical, focusing on ML engineering skills that you’ll use in industry rather than academic theory.

The course is designed to be community-driven, encouraging you to learn together, share your progress, and help each other succeed. This collaborative approach mirrors real-world ML engineering environments and builds valuable professional networks.