Module 1: Introduction to Machine Learning - Machine Learning for Intelligent Systems & Robotics

This module frames the whole course: what machine learning is, the three broad learning paradigms, and the terminology and workflow we will use for the rest of the semester.

What You’ll Learn¶

Supervised, unsupervised, and reinforcement learning — and when each applies
The basic terminology: samples, features, labels, training, inference
The canonical ML workflow: preprocessing → training → model selection → evaluation
A roadmap of the techniques covered in this course

Lecture Materials¶

📝 Lecture Notes (PDF)
📓 Chapter notebook: Giving Computers the Ability to Learn from Data

Lecture Videos¶

Part 1: Introduction and Types of Machine Learning | CAP 6606 — Module 1, Part 1¶

Part 2: Core Machine Learning Problems and Workflow | CAP 6606 — Module 1, Part 2¶

Prerequisites¶

Basic Python
Introductory linear algebra and probability

Reference¶

Raschka & Mirjalili, Machine Learning with PyTorch and Scikit-Learn, Chapter 1.