Unit rationale, description and aim
Artificial intelligence (AI) is the intelligence demonstrated by machines, devices, agents or computer programs, in addition to the natural intelligence displayed by humans and animals. Deep learning is a type of machine learning and artificial intelligence (AI) that imitates the way humans gain certain types of knowledge. It is the de-facto method for a wide range of emerging AI tasks from computer vision, natural language processing, anomaly detection, to reinforcement learning.
This unit will cover essential aspects of deep learning and emerging topics in AI, both theoretically and practically. This includes understanding, designing and implementing of elements of deep learning models and algorithms as well as emerging AI topics with Python Keras. This unit features integrating Microsoft Azure AI Fundamentals to understand standards and design principals of AI solutions in technology industry giant. The aim of this unit is to equip students with essential concepts and techniques of deep learning and artificial intelligence (AI), enabling them to design and develop AI-enabled applications that enhance the quality of life and address real-world challenges.
Learning outcomes
To successfully complete this unit you will be able to demonstrate you have achieved the learning outcomes (LO) detailed in the below table.
Each outcome is informed by a number of graduate capabilities (GC) to ensure your work in this, and every unit, is part of a larger goal of graduating from ACU with the attributes of insight, empathy, imagination and impact.
Explore the graduate capabilities.
Demonstrate theoretical knowledge of data science,...
Learning Outcome 01
Apply practical programming skills, machine learni...
Learning Outcome 02
Critically evaluate machine learning models for re...
Learning Outcome 03
Critically analyse the issue of machine bias and i...
Learning Outcome 04
Content
Topics will include:
· Recap of ML project design
· Introduction to AI and AI project design
· Introduction to deep learning
· Deep neural networks/Convolutional neural networks
· Deep neural network architectures, training, inference, and testing
· Computer vision
· Natural language processing
· Anomaly detection
· Reinforcement learning
· Microsoft Azure AI Fundamentals
· Fundamental use cases for AI that makes common good and builds better stewardship
· AI ethics and safety with impact on the common good and human dignity
Assessment strategy and rationale
The assessment tasks are deliberately sequenced to scaffold student learning and ensure attainment of the unit learning outcomes and graduate attributes. The initial programming practical provides students with opportunities to apply core machine learning techniques, building foundational technical competence and reinforcing problem‑solving skills. The second assessment extends this by combining question‑answering with programming tasks on essential aspects of AI, requiring students to demonstrate both conceptual understanding and applied skills in a structured, practice‑oriented format. The final project consolidates and advances learning by engaging students in the end‑to‑end development of an AI and machine learning solution, requiring them to integrate technical knowledge with practical programming skills while critically considering issues of AI ethics and safety. This progression from foundational exercises to applied practice to comprehensive project work ensures students develop both technical proficiency and reflective judgement, directly supporting achievement of the unit’s learning outcomes and preparing them for professional challenges in AI and machine learning. The assessments for this unit are designed to demonstrate the achievement of each learning outcome. To pass this unit, you are required to obtain an overall mark of at least 50%.
Overview of assessments
Task 1: Machine learning and AI programming pract...
Task 1: Machine learning and AI programming practical.
The first assessment item consists of several programming tasks. The purpose is to comprehensively assess students’ practical machine learning and AI skills using python and sophisticated machine learning/AI models. The deliverable is python code and solution/algorithm description.
Submission type: Individual
Assessment Method: Practical Tasks
Artefact: Codes and comments in Jupyter Notebook
30%
Task 2: AI-900 Microsoft Azure AI Fundamentals ce...
Task 2: AI-900 Microsoft Azure AI Fundamentals certificate exam
The final assessment is a Microsoft certificate exam. The purpose is to assess students’ overall AI and machine learning knowledge and understanding in Microsoft certificate level.
Submission type: Individual
Assessment Method: Certification Exam via Certiport Systyem
Artefact: Exam
40%
Task 3: Artificial intelligence and machine learn...
Task 3: Artificial intelligence and machine learning project
The final assessment is a group-based AI project including machine learning. The purpose is to assess students’ overall AI and machine learning knowledge and understanding as well as collaborative AI implementation skills with consideration of AI ethics and safety through working on a real-world complex AI and machine learning problem. The group deliverable will consist of both report and code.
Submission type: Individual
Assessment Method: project
Artefact: Codes, comments, and summary in Jupyter Notebook
30%
Learning and teaching strategy and rationale
This unit is offered in two delivery modes—Attendance and Online—to support diverse learning needs and maximise access for isolated or marginalised groups.
Attendance Mode
Students attend weekly face-to-face classes at designated locations and engage directly with lecturers to support achievement of learning outcomes. The unit requires preparation before workshops (typically around one hour) and at least one hour of consolidation afterwards. Online learning platforms provide additional preparatory and practice activities to reinforce learning.
Online Mode
The online mode enables students to explore core disciplinary knowledge through both synchronous and asynchronous learning. Weekly discussion activities and active learning tasks encourage the application of theoretical concepts in professional contexts. Engagement with peers supports constructive learning, and students receive regular, timely feedback throughout the semester.
Students receive regular and timely feedback throughout the semester to support their progress and ongoing academic development.
Students should anticipate approximately 150 hours of total study for this unit, including class attendance, readings, online participation, and assessment tasks.
Representative texts and references
Required text(s)
Aurélien Géron, 2022. Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd Edition, O'Reilly Media, Inc. Wei-Ming Lee. Python Machine Learning, Wiley.
Recommended references
Brownlee, J. (2021). Deep Learning for Time Series Forecasting: Predict the Future with MLPs, CNNs and LSTMs in Python. Machine Learning Mastery.
Géron, A. (2022). Machine Learning Engineering with Python: A Guide to Building Production-Ready Machine Learning Systems. O’Reilly Media.
Kelleher, J. D., Namee, B., & D’Arcy, A. (2023). Fundamentals of Machine Learning for Predictive Data Analytics: Algorithms, Worked Examples, and Case Studies (2nd ed.). MIT Press.
Raschka, S., & Mirjalili, V. (2024). Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2 (5th ed.). Packt Publishing.
Goodfellow, I., Bengio, Y., & Courville, A. (2024). Deep Learning (2nd ed.). MIT Press.
Jean, H. (2020). Essential Math for Data Science: Take Control of Your Data with Fundamental Calculus, Linear Algebra, Probability, and Statistics. O’Reilly Media
Artasanchez, A., & Joshi, P. (2020). Artificial Intelligence with Python: Your Complete Guide to Building Intelligent Apps Using Python 3.x (2nd ed.). Packt Publishing.
Russell, S., & Norvig, P. (2020). Artificial Intelligence: A Modern Approach (4th ed.). Pearson.
Neapolitan, R. E., & Jiang, X. (2018). Artificial Intelligence: With an Introduction to Machine Learning (2nd ed.). Chapman & Hall/CRC.
Géron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (2nd ed.). O’Reilly Media.