https://courseoutline.auckland.ac.nz/dco/course/COMPSYS/721/1253

COMPSYS 721 : Machine Intelligence and Deep Learning

Engineering

2025 Semester One (1253) (15 POINTS)

Course Prescription

Explores essential concepts and technologies in state-of-the-art deep neural network architectures, including convolutional neural networks, decision trees, random forests, similarity learning, recurrent neural networks, and long short-term memory networks. Includes hands-on experience combining hardware components with software implementations.

Course Overview

The class "Machine Intelligence and Deep Learning" (COMPSYS721) overviews essential concepts and technologies in deep neural network architectures. During the 12-week course, students will learn to implement and train their neural networks and gain a detailed understanding of cutting-edge research in machine learning and deep neural networks. Furthermore, through the labs and the course projects, students will develop the toolset for setting up deep learning tasks and practical engineering tricks for training and fine-tuning deep neural networks. The final project will be on training the Jetson nano module to do object tracking and face recognition tasks.
The course will mainly discuss the following topics:
 Convolutional Neural Networks (CNNs): Students delve into CNN principles, advanced methods, and hands-on practice to equip them for applying CNNs in real-world situations. The curriculum covers both theoretical and practical implementation using Python and popular frameworks.
 Decision Trees and Random Forests: Students learn how these algorithms organize data for predictions, with Random Forests expanding on Decision Trees to handle more intricate data sets while enhancing accuracy.
Similarity Learning with Siamese Neural Networks: This section introduces how to gauge object similarity using Siamese Networks utilizing machine learning techniques. It explores applications like face recognition, examines loss functions like Triplet loss, and discusses One Shot and Few Shot Learning.
 Recurrent Neural Networks (RNNs) and LSTM: The course explores RNNs tailored for time series data, introducing LSTM networks to tackle long-term dependencies for improved performance in tasks like language translation and time series forecasting.
Throughout the course, participants engage in lab exercises and real-world scenarios to practice their skills in applying these algorithms to machine learning challenges. There will be projects using hardware components and software implementations.

Course Requirements

Prerequisite: COMPSYS 306, and COMPSYS 302 or SOFTENG 306 or 351 Restriction: COMPSYS 726

Capabilities Developed in this Course

Capability 1: People and Place
Capability 2: Sustainability
Capability 3: Knowledge and Practice
Capability 4: Critical Thinking
Capability 5: Solution Seeking
Graduate Profile: Bachelor of Engineering (Honours)

Learning Outcomes

By the end of this course, students will be able to:
  1. Develop Implement and train deep neural networks (Capability 1.1 and 3.2)
  2. Demonstrate an understanding of Gain a detailed understanding of cutting-edge research in machine learning and deep (Capability 2.1, 3.1, 3.2 and 5.1)
  3. Apply Develop the toolset for setting up deep learning tasks and practical engineering tricks for training and fine-tuning deep neural networks. (Capability 2.1, 3.2, 4.2 and 5.1)
  4. Be able to Train the Jetson Nano module to do object tracking and face recognition tasks. (Capability 3.1, 3.2 and 5.1)
  5. Analyse Engage in lab exercises and real-world scenarios to practice skills in applying algorithms to machine learning challenges. (Capability 2.1, 3.2 and 4.1)
  6. Demonstrate an understanding of Present and document project outcomes effectively (Capability 2.1, 3.1, 3.2, 4.2 and 5.1)

Assessments

Assessment Type Percentage Classification
Laboratories 32% Individual Coursework
Test 10% Individual Coursework
Case Studies 28% Individual Coursework
Project 30% Group & Individual Coursework
4 types 100%
Assessment Type Learning Outcome Addressed
1 2 3 4 5 6
Laboratories
Test
Case Studies
Project

A passing mark is 50% or higher for each assessment category, according to the University policy.

All assessments are compulsory for all students and DNC for the course will be awarded if the student has not completed labs and not submitted the deliverable for any component (assignment or project) as required. The details of each assessment and requirements will be given via the course page on Canvas.

By default, late submissions are not allowed, unless specific late submission penalties are released on Canvas.

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 and 5 hours of work on assignments and/or test preparation.

Delivery Mode

Campus Experience

Attendance is must/expected at scheduled activities including must for the labs/ expected for the lectures to receive credit for components of the course.
Lectures will be available as recordings. Other learning activities including labs/studios will not be available as recordings.
The course will not include live online events including group discussions/tutorials.
Attendance on campus is required for the test.
The activities for the course are scheduled as a standard weekly timetable.

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.

Health & Safety

Health and safety conditions when using MD'S and/or ESE research labs require a certificate of passing induction training. Students must ensure they are familiar with their Health and Safety responsibilities, as described in the university's Health and Safety policy

Student Feedback

At the end of every semester 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 and respond with summaries and actions.

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

Class Representatives in each class can take feedback to the department and faculty staff-student consultative committees.

The course will run for the second time in 2025.Based on the 2024 SET results, students' feedback was excellent, and we continue to follow the same methods with minor amendments on some components. 

Academic Integrity

The University of Auckland will not tolerate cheating, or assisting others to cheat, and views cheating in coursework, tests and examinations 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. A student's assessed work may be reviewed against electronic source material using computerised detection mechanisms. Upon reasonable request, students may be required to provide an electronic version of their work for computerised review.

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.

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 http://disability.auckland.ac.nz

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 https://www.auckland.ac.nz/en/students/academic-information/exams-and-final-results/during-exams/aegrotat-and-compassionate-consideration.html.

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 your assessment is fair, and not compromised. Some adjustments may need to be made in emergencies. You will be kept fully informed by your course co-ordinator, and if disruption occurs you should refer to the University Website for information about how to proceed.

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 https://www.auckland.ac.nz/en/students/forms-policies-and-guidelines/student-policies-and-guidelines/student-charter.html.

Disclaimer

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 you may be asked to submit your 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. The final decision on the completion mode for a test or examination, and remote invigilation arrangements where applicable, will be advised to students at least 10 days prior to the scheduled date of the assessment, or in the case of an examination when the examination timetable is published.