Program Overview

Course Overview

The course AIML 335, Machine Learning, teaches fundamental concepts and mathematical techniques that underlie much of machine learning (ML). Topics include an introduction to learning theory, optimisation for ML, unsupervised learning, learning with latent variables, generative models, kernels, aspects of information theory, deep learning, continual/online learning, transfer learning, and anomaly detection.

Course Details

• Dates: 6 Jul 2026 to 8 Nov 2026
• Starts: Trimester 2
• Fees:
  • NZ$1,083.45 for domestic students
  • NZ$5,806.35 for international students
• Lecture Start Times:
  • Monday 1.10pm
  • Thursday 1.10pm
• Campus: Kelburn
• Estimated Workload: Approximately 150 hours or 8.3 hours per week for 18 weeks
• Points: 15

Entry Restrictions

• Prerequisites: one of (AIML 320, AIML 331, AIML 332); one of (COMP 261, NWEN 241, SWEN 221); one of (MATH 177, MATH 277, STAT 292)
• Corequisites: None
• Restrictions: None

Taught By

The course is taught by the School of Engineering and Computer Science — Faculty of Science and Engineering.

Key Dates

Important dates, including mid-trimester teaching breaks, can be found on the University's key dates calendar. Assessment dates will be announced once the course has begun.

About This Course

Machine Learning (ML) is the study of computational systems that can learn from data and improve their performance on tasks over time. AIML335 presents core theories and techniques that support the development of such systems, covering advanced concepts in machine learning.

Course Learning Objectives

Students who pass this course should be able to:

1. Explain the key Machine Learning concepts and the related mathematical techniques.
2. Compare and contrast alternative approaches to machine learning, or different deep net architectures, with reference to the underlying theory.
3. Use a mathematical framework to derive details for the application of algorithms in specific scenarios.
4. Identify common pitfalls or misapplications of machine learning and be able to relate those to underlying theory.

How This Course Is Taught

This course will be offered in-person, with lectures recorded and made available online. There will typically be two lectures and one tutorial per week.

Assessment

• Final Exam: 40%
• Assignments (x3): 45%
• Test: 15%

Mandatory Requirements

To pass this course, students must achieve an overall pass mark of at least 50% and:

1. Achieve at least 40% on the combination of the Test and the Final Exam to demonstrate ability to apply their understanding of Machine Learning techniques independently.

Lecture Times and Rooms

Lecture times and rooms will be announced.

What You'll Need to Get

No specific texts or equipment are required for this course.

Course Staff

• Dr Heitor Gomes: Course Coordinator
• Professor Bastiaan Kleijn: Lecturer
• Dr Marcus Frean: Lecturer