COMP328 Fundamentals of Machine Learning

Module 1 of 6

Foundations of Machine Learning

Three units that give you the vocabulary, the data skills, and the tooling you need before you train your first model. No machine learning experience is assumed — only the programming and statistics prerequisites for the course.

3 units 27 tutorials 3 unit quizzes ~18 hours estimated

Module at a glance

Units 3 — concepts, data, and tooling
Tutorials 27 — nine per unit
Quizzes 3 — one at the end of each unit
Study time ~18 hours total

Learning outcomes

What you will be able to do

Module 1 is deliberately conceptual and practical in equal measure. By the end of Unit 3 you will have the mental model and the working environment to begin modelling.

By the end of this module you will be able to

  • Explain what machine learning is, how it differs from classical programming, and where it sits within the broader field of artificial intelligence.
  • Distinguish between supervised, unsupervised, and reinforcement learning, and identify which paradigm suits a given problem.
  • Describe the stages of the machine learning lifecycle, from problem framing through to monitoring in production.
  • Identify the characteristics of structured and unstructured data, and explain the roles of features, labels, and target variables.
  • Recognise common data quality problems and select appropriate preprocessing steps to address them.
  • Apply the Python data science stack — NumPy, Pandas, Matplotlib, and Scikit-Learn — to load, inspect, clean, and visualise a dataset.
  • Split a dataset into training, validation, and test partitions, and explain why each partition exists.

No prior machine learning required

If you can write a Python function and read a basic statistical summary, you are ready for this module. Unit 3 rebuilds your Python tooling from the ground up specifically for data work, so any gaps there will be filled in context.

Units & tutorials

Three units, twenty-seven tutorials

Work through the units in order. Each tutorial is self-contained and follows the same nine-part structure, so the rhythm stays predictable while the ideas deepen.

Unit 1 9 tutorials · ~6 hours

Introduction to Machine Learning

Where the field came from, what it actually does, and the vocabulary you will use for the rest of the course.

Unit overview Start T-01
Unit 3 9 tutorials · ~6 hours

Python ML Ecosystem

A hands-on tour of the tools you will use for the rest of the course, ending with your first complete end-to-end workflow.

Unit overview Start T-01

How to work through it

A steady rhythm, one tutorial at a time

Module 1 is not a race. The concepts here recur constantly in later modules, so the time you spend on them pays compound interest.

  1. Read the tutorial

    Work through all nine sections in order. The worked examples and self-check questions are part of the reading, not optional extras.

  2. Run the code

    Open the accompanying notebook and execute every cell yourself. From Unit 3 onward, the code is the point.

  3. Answer the self-checks

    If you cannot answer a self-check question without looking back, re-read that section before moving on.

  4. Finish with the unit quiz

    Each unit ends with a short quiz. Score it honestly — it is a diagnostic, not a hurdle.

Assessment

How this module is assessed

Module 1 carries three unit quizzes worth a portion of the 15% quiz component of your final grade. There is no assignment in this module — the first assignment lands in Module 2.

  • Quiz 1 Introduction to Machine Learning — 12 questions, unweighted diagnostic Unit 1
  • Quiz 2 Data Fundamentals — 12 questions, unweighted diagnostic Unit 2
  • Quiz 3 Python ML Ecosystem — 15 questions, counts toward your quiz grade Unit 3

Looking ahead

Everything you build in Module 1 feeds directly into Module 2, where you will train your first regression models using the same datasets and the same Scikit-Learn workflow you set up in Unit 3.

👤