Overview

This unit of study aims to equip engineers with both theoretical knowledge and practical skills to design, implement, and evaluate Artificial Intelligence (AI) and Machine Learning (ML) solutions for complex engineering challenges. It emphasises developing proficiency in selecting suitable algorithms, optimising system performance, and considering ethical aspects, while bridging the gap between Artificial Intelligence (AI) theory and engineering applications. The course prepares professionals to deploy intelligent systems efficiently and communicate technical solutions across multidisciplinary teams.

Requisites

Prerequisites
COS10009 Introduction to Programming

AND
100 credit points in BEng or BCompSc or related double degrees.


Teaching periods
Location
Start and end dates
Last self-enrolment date
Census date
Last withdraw without fail date
Results released date

Learning outcomes

Students who successfully complete this unit will be able to:

  • Design, develop, deploy, and maintain Machine Learning (ML)/Artificial Intelligence (AI) pipelines by selecting and training datasets to address complex, multidisciplinary engineering problems (A4, A5, A6, K1, K2, S1)
  • Explain and compare a range of Artificial Intelligence (AI), Machine Learning (ML), & Deep Learning (DL) algorithms in terms of their structure, function, and real-world applicability (A1, A2, A4, K3, K4, S2)
  • Evaluate and justify the selection of AI techniques based on computational efficiency, ethical implications, and problem constraints for solving diverse computational engineering challenges (A3, K4, K5, K6, S2, S3)
  • Communicate clearly and effectively technical concepts, project outcomes, and design decisions through written reports and oral presentations (A2, A5, A6, A7, S3, S4)

Teaching methods

Hawthorn

Type Hours per week Number of weeks Total (number of hours)
Live Online
Lecture		 1.00  12 weeks  12
Online
Lecture		 1.00  12 weeks  12
On-campus
Class		 2.00  12 weeks  24
Unspecified Activities
Various		 8.50  12 weeks  102
TOTAL     150

Assessment

Type Task Weighting ULO's
Applied Project Individual/Group  40 - 60%  1,2,3,4 
Portfolio Individual  40 - 60%  1,2,3 

Hurdle

To pass this unit, you must:

(i) Achieve an overall mark for the unit of 50% or more, and
(ii) Complete the project to an acceptable standard.
A rubric will be used to determine if students have met the acceptable standard. The rubric is available on Canvas, and
(iii) Achieve a minimum of 50% or more on the Portfolio (must pass at least 50% of the portfolio assessment activities).

Students who do not successfully achieve hurdle requirements (ii) and (iii) in full will receive a maximum of 45% as the total mark for the unit.

Content

  • Utilising Machine Learning (ML) paradigms such as Supervised, Unsupervised, and Reinforcement Learning.
  • Understanding foundation models vs. traditional machine learning trade-offs.
  • Data-Centric Artificial Intelligence (AI) Development.
  • Automated Data Pipelines and Machine Learning Operations (MLOps) for reproducibility.
  • Algorithm Selection Frameworks for Production-Grade Machine Learning (ML) Specifications.
  • Artificial Intelligence (AI) for Emerging Engineering Applications & Technologies.

Study resources

Reading materials

A list of reading materials and/or required textbooks will be available in the Unit Outline on Canvas.