COMPSCI 762 : Foundations of Machine Learning


2023 Semester One (1233) (15 POINTS)

Course Prescription

Machine learning is a branch of artificial intelligence concerned with making accurate, interpretable, computationally efficient, and robust inferences from data to solve a given problem. Students will be introduced to the foundations of machine learning and will gain practical skills to solve different problems. Students will explore research frontiers in machine learning.

Course Overview

This course will provide the foundations of machine learning. Students will explore what it means to learn models from data (without explicitly coding knowledge), including concepts from computational and statistical learning theory to understand, reason and potentially develop new methods for automated learning.
Through this course, students will learn the fundamental algorithmic principles, and the challenges, involved in getting computers to learn from data, as well as develop practical skills to solve different learning problems and the ability to critically evaluate the modelling results. This will allow students to specialise further in advanced areas of data science, machine learning or artificial intelligence. This course provides a broad introduction to machine learning. The course expects mastery of fundamental mathematical skills, foundations in statistical analysis and concepts, good programming skills (the preferred programming language for this course is Python, or possibly R), and a good understanding of algorithm design and computational complexity.

Course Requirements

Prerequisite: COMPSCI 220 or 717, and 15 points from DATASCI 100, STATS 101, 108, and COMPSCI 225 or MATHS 254 Restriction: COMPSCI 361

Capabilities Developed in this Course

Capability 1: Disciplinary Knowledge and Practice
Capability 2: Critical Thinking
Capability 3: Solution Seeking
Capability 4: Communication and Engagement
Capability 5: Independence and Integrity

Learning Outcomes

By the end of this course, students will be able to:
  1. Explain and critique the theory that underpins machine learning (i.e. fundamental principles of learning as a computational process). This means understanding relevant concepts from both computer science and statistics (e.g, bias/variance tradeoff, minimum description length principle, kernel functions). (Capability 1, 2, 3 and 4)
  2. Explain and critique the basic algorithmic principles and challenges involved in getting computers to learn from both labelled data (as in supervised learning) and unlabeled data (as in unsupervised learning), including the challenges involved in data preprocessing, model evaluation, model selection, model complexity. (Capability 1, 2, 3 and 4)
  3. Compare and contrast the different machine learning techniques for supervised learning (e.g. classification and regression) and unsupervised learning (e.g. clustering) used for different dataset types. (Capability 1, 2 and 3)
  4. Develop and demonstrate a good understanding of machine learning theory by implementing machine learning algorithms from scratch, developing modifications of existing machine learning algorithms and applying existing machine learning algorithm implementations, using both core and specialized programming packages in Python (or R). (Capability 1, 2, 3, 4 and 5)
  5. Design and implement appropriate evaluation procedures in machine learning for different scenarios involving different dataset types and machine learning algorithms. (Capability 1, 2, 3 and 5)
  6. Develop the ability to critically interpret and evaluate the results of a machine learning algorithm run on a specific dataset, e.g, categorical, continuous, mixed-type data. (Capability 1, 2, 3, 4 and 5)


Assessment Type Percentage Classification
Assignments 35% Individual Coursework
Tutorial assessment 5% Group Coursework
Test 20% Individual Test
Final Exam 40% Individual Examination
Assessment Type Learning Outcome Addressed
1 2 3 4 5 6
Tutorial assessment
Final Exam


Tuākana Science is a multi-faceted programme for Māori and Pacific students providing topic specific tutorials, one-on-one sessions, test and exam preparation and more. Explore your options at

Key Topics

  • Fundamentals of machine learning theory (e.g. bias/variance theory), model evaluation and validation (e.g., cross-validation, model performance measures such as accuracy, precision, recall, ROC/AUC)
  • Supervised learning methods (e.g., decision trees, support vector machines, neural networks)
  • Unsupervised learning methods (e.g., clustering, association rule mining)

Workload Expectations

This course is a standard 15-point course and students are expected to spend 10 hours per week involved in each 15-point course that they are enrolled in.

For this course, you can expect:

  • 3 hours of lectures
  • A 1-hour tutorial
  • 3 hours of reading and thinking about the content
  • 3 hours of work on assignments per week
As well as, approximately  30 hours for test/exam preparation across the semester.

Delivery Mode

Campus Experience

Attendance is expected at scheduled activities including tutorials to complete components of the course.
Lectures will be available as recordings. Other learning activities including tutorials will be available as recordings.
The course will not include live online events.
Attendance on campus is required for the test/exam.
The activities for the course are scheduled as a standard weekly timetable delivery.

Learning Resources

Course materials are made available in a learning and collaboration tool called Canvas which also includes reading lists and lecture recordings (where available).

Please remember that the recording of any class on a personal device requires the permission of the instructor.

Note: The list bellow is provided in chronological order; most of the books can be found online in pdf format. There is no single book that covers all topics. We will typically recommend which resource (book chapter) is best aligned with the specific lectures during the course delivery.
Textbooks: Textbooks covering fundamentals of machine learning theory and different algorithms for supervised and unsupervised learning.
  • Mitchell, T. M. (1997). Machine learning. New York: McGraw-Hill. 
  • Tan, P.-N., Steinbach, M., & Kumar, V. (2005). Introduction to data mining (1st ed). Boston: Pearson Addison Wesley.
  • Bishop, C. M. (2006). Pattern Recognition and Machine Learning (1st ed. 2006. Corr. 2nd printing 2011). New York, NY: Springer-Verlag New York Inc. 
  • Han, J., Kamber, M., & Pei, J. (2014). Data Mining (3rd Revised ed.). Morgan Kaufmann Publishers. 
  • Witten, I. H., Frank, E., Hall, M., & Pal, C. (2016). Data Mining (4th edition). Retrieved from 
  • Burkov, A. (2019) The Hundred-Page Machine Learning Book
Resources with a focus on data streams:
  • Gama, J. (2010). Knowledge discovery from data streams. Retrieved from
  • Bifet, A., Gavaldà, R., Holmes, G., & Pfahringer, B. (2018). Machine Learning for Data Streams with Practical Examples in MOA. Retrieved from

Student Feedback

During the course Class Representatives in each class can take feedback to the staff responsible for the course and staff-student consultative committees.

At the end of the course students will be invited to give feedback on the course and teaching through a tool called SET or Qualtrics. The lecturers and course co-ordinators will consider all feedback.

Your feedback helps to improve the course and its delivery for all students.

 The course was just re-designed, and the feedback was  very positive. We might consider some minor modification in the last assignment . But, once the teaching team is confirmed we will discuss this.

Academic Integrity

The University of Auckland will not tolerate cheating, or assisting others to cheat, and views cheating in coursework as a serious academic offence. The work that a student submits for grading must be the student's own work, reflecting their learning. Where work from other sources is used, it must be properly acknowledged and referenced. This requirement also applies to sources on the internet. A student's assessed work may be reviewed against online source material using computerised detection mechanisms.

Class Representatives

Class representatives are students tasked with representing student issues to departments, faculties, and the wider university. If you have a complaint about this course, please contact your class rep who will know how to raise it in the right channels. See your departmental noticeboard for contact details for your class reps.


The content and delivery of content in this course are protected by copyright. Material belonging to others may have been used in this course and copied by and solely for the educational purposes of the University under license.

You may copy the course content for the purposes of private study or research, but you may not upload onto any third party site, make a further copy or sell, alter or further reproduce or distribute any part of the course content to another person.

Inclusive Learning

All students are asked to discuss any impairment related requirements privately, face to face and/or in written form with the course coordinator, lecturer or tutor.

Student Disability Services also provides support for students with a wide range of impairments, both visible and invisible, to succeed and excel at the University. For more information and contact details, please visit the Student Disability Services’ website

Special Circumstances

If your ability to complete assessed coursework is affected by illness or other personal circumstances outside of your control, contact a member of teaching staff as soon as possible before the assessment is due.

If your personal circumstances significantly affect your performance, or preparation, for an exam or eligible written test, refer to the University’s aegrotat or compassionate consideration page

This should be done as soon as possible and no later than seven days after the affected test or exam date.

Learning Continuity

In the event of an unexpected disruption, we undertake to maintain the continuity and standard of teaching and learning in all your courses throughout the year. If there are unexpected disruptions the University has contingency plans to ensure that access to your course continues and course assessment continues to meet the principles of the University’s assessment policy. Some adjustments may need to be made in emergencies. You will be kept fully informed by your course co-ordinator/director, and if disruption occurs you should refer to the university website for information about how to proceed.

The delivery mode may change depending on COVID restrictions. Any changes will be communicated through Canvas.

Student Charter and Responsibilities

The Student Charter assumes and acknowledges that students are active participants in the learning process and that they have responsibilities to the institution and the international community of scholars. The University expects that students will act at all times in a way that demonstrates respect for the rights of other students and staff so that the learning environment is both safe and productive. For further information visit Student Charter


Elements of this outline may be subject to change. The latest information about the course will be available for enrolled students in Canvas.

In this course students may be asked to submit coursework assessments digitally. The University reserves the right to conduct scheduled tests and examinations for this course online or through the use of computers or other electronic devices. Where tests or examinations are conducted online remote invigilation arrangements may be used. In exceptional circumstances changes to elements of this course may be necessary at short notice. Students enrolled in this course will be informed of any such changes and the reasons for them, as soon as possible, through Canvas.

Published on 31/10/2022 09:29 a.m.