Unit rationale, description and aim
Artificial intelligence is driving transformative advances across domains such as automation, natural language processing, computer vision, and healthcare analytics. Deep learning underpins these innovations by enabling data-driven decision-making and intelligent system design.
This unit explores advanced deep learning architectures, including convolutional neural networks (CNNs), sequence-based models such as recurrent neural networks (RNNs) and transformers, graph neural networks, and generative models. Students will apply these methods to real-world datasets, optimise model performance, interpret results, and evaluate trade-offs involving overfitting, fairness, and computational efficiency. The unit emphasises responsible and reproducible practices in model development, testing, and deployment through applied tasks and case studies. By integrating theoretical understanding with hands-on implementation, students will develop the capability to design, train, and evaluate deep learning solutions that are robust. The unit supports ACU’s mission of ethical innovation and aligns with the UN Sustainable Development Goals, particularly SDG 9 (Industry, Innovation and Infrastructure) and SDG 12 (Responsible Consumption and Production).
The aim of this unit is to develop students’ ability to apply deep learning techniques responsibly to solve complex real-world problems.
Campus offering
No unit offerings are currently available for this unit.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.
Design and implement deep learning models to addre...
Learning Outcome 01
Evaluate model performance through experimentation...
Learning Outcome 02
Interpret and communicate deep learning results us...
Learning Outcome 03
Apply responsible AI principles in the development...
Learning Outcome 04
Content
Topics will include:
- Introduction to Deep Learning Foundations.
- Neural Network Architectures and Activation Functions
- Model Training, Regularisation and Optimisation
- Convolutional Neural Networks (CNNs)
- Transfer Learning and Model Evaluation
- Graft Neural Networks
- Neural Networks for Sequence Data - RNNs
- Generative Models
- Applied Implementation and Responsible AI
Assessment strategy and rationale
The assessment strategy is designed to progressively build students’ technical proficiency, analytical capability, and ethical awareness in applying deep learning techniques within an authentic online learning environment. Assessments are scaffolded to align with learning outcomes and to promote active engagement, reflection, and responsible practice.
Assessment 1 (Technical Notebook) develops practical understanding of neural network architectures, training, and evaluation using frameworks such as TensorFlow or PyTorch. It encourages systematic experimentation, documentation, and analysis of results, reinforcing academic integrity through transparent and verifiable outputs.
Assessment 2 (Applied Deep Learning Project) integrates advanced model design, optimisation, and evaluation using real-world datasets. It mirrors professional workflows, strengthening students’ ability to plan, communicate insights, and apply deep learning methods ethically and effectively.
Assessment 3 (Reflective Report) deepens critical thinking through evaluation of reproducibility, transparency, and fairness in published research. It fosters ethical reasoning and awareness of sustainability and interpretability in AI practices.
Together, these assessments cultivate practical competence, critical insight, and ethical responsibility, aligning with ACU’s mission of innovation for the common good and the UN Sustainable Development Goals (SDG 9 and SDG 12).
To pass the unit, students must achieve all learning outcomes and an overall grade of 50% or higher.
Overview of assessments
Assessment Task 1: Technical Notebook – Neural Ne...
Assessment Task 1: Technical Notebook – Neural Network Implementation and Analysis
Students document and analyse a series of implemented neural network models using frameworks such as TensorFlow or PyTorch.
30%
Assessment Task 2: Applied Deep Learning Project ...
Assessment Task 2: Applied Deep Learning Project
Students design, implement, and optimise advanced deep learning models using real-world datasets. The project mirrors authentic professional workflows, strengthening students’ ability to plan, evaluate, and communicate insights, and to apply deep learning methods ethically, transparently, and effectively.
40%
Assessment Task 3: Reflective Report - Reproducib...
Assessment Task 3: Reflective Report - Reproducible Deep Learning Models
Students critically evaluate issues of reproducibility, transparency, fairness, and sustainability in published deep learning research. The report deepens ethical reasoning and reflective practice, fostering awareness of the interpretability and social implications of AI in research and professional contexts.
30%
Learning and teaching strategy and rationale
This unit adopts a research-informed and practice-oriented approach designed to develop both conceptual understanding and applied capability. Learning activities are structured around authentic challenges relevant to deep neural networks, encouraging students to connect theory with practice through independent study, guided exercises, and reflective engagement.
Students will participate in structured learning experiences such as readings, multimedia resources, problem-based tasks, and facilitated discussions that support analysis, critical thinking, and knowledge application. Opportunities for collaborative inquiry and consultation are provided to consolidate learning and enhance professional and academic growth.
Representative texts and references
Bishop, C. M. (2023). Pattern Recognition and Machine Learning. Springer.
Chollet, F. (2021). Deep Learning with Python (2nd ed.). Manning Publications.
Géron, A. (2023). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow (3rd ed.). O’Reilly Media.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
Labonne, M. (2023). Hands On Graph Neural Networks Using Python. Packt Publishing.
Leben, D. (2025). AI Fairness: Designing Equal Opportunity Algorithms. MIT Press Academic.
Ruan, H., Li, Y., & Zhang, H. (2025). Graph Neural Networks in Action. Manning Publications.
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Philip, S. Y. (2022). Graph Neural Networks: Foundations, Frontiers and Applications. Springer.
Zhang, A., Lipton, Z. C., Li, M., & Smola, A. J. (2020). Dive into Deep Learning. Open Source.
Frameworks and Standards:
Google Colab and Jupyter Notebooks for experimentation
Keras — high-level neural network API, part of TensorFlow
TensorFlow, PyTorch, and Keras frameworks
Scikit-learn and Hugging Face Transformers libraries