COMP329 Advanced ML & Deep Learning

Computing & Information Systems · Advanced course

COMP329 Advanced Machine Learning and Deep Learning

Move beyond the fundamentals. Design, train, evaluate and deploy modern neural networks — from optimisation and convolutional architectures to transformers, generative models and the engineering practices that make deep learning work in production.

Explore the curriculum View syllabus
6 modules 18 units 152 tutorial pages 15 credits

Course overview

From models that work to models that ship

COMP329 is the capstone course of the AI sequence. It takes the machine learning foundations from COMP328 and develops them into the architectures, training techniques and engineering practices used in contemporary deep learning systems.

The course begins with the mathematics of learning at scale: gradient-based optimisation, regularisation and principled model evaluation. From there it builds upwards through neural network architectures — fully connected, convolutional, recurrent and transformer — before turning to generative modelling and representation learning.

Throughout, the emphasis is on implementation. You will build networks from first principles before using established frameworks, so that you understand what the libraries are doing on your behalf and can debug them when they fail.

The final third of the course addresses the realities of applied deep learning: data pipelines, transfer learning, compute constraints, interpretability, fairness and safe deployment. You finish with a capstone that takes a deep learning system from problem definition to a working, documented, evaluated artefact.

Prerequisites

COMP328 Fundamentals of Machine Learning, or equivalent. You should be comfortable with Python, vectors and matrices, derivatives, and basic probability. COMP326 provides the data-handling background assumed here.

Compute access

Laboratory sessions run on shared GPU workstations. All assignments are designed to be completable on free cloud notebook tiers, so no personal GPU hardware is required.

Course details

Level
Undergraduate · Final year / advanced
Credits
15 credits, one semester
Delivery
2 lectures and 1 GPU laboratory session per week, plus guided self-study
Language & tools
Python 3, PyTorch, TensorFlow/Keras, scikit-learn, Hugging Face Transformers
Assessment
5 assignments, 18 unit quizzes, midterm, final exam and a capstone project
Neural networks Transformers Generative models Responsible AI
Course structure at a glance
Module Focus Units Tutorials
1 · Advanced ML Foundations Optimisation, regularisation, generalisation and rigorous evaluation 3 26
2 · Neural Networks & Deep Learning Backpropagation, training at depth and convolutional architectures 3 27
3 · Sequence Models & Attention Recurrent networks, attention, transformers and transfer learning 3 25
4 · Generative & Unsupervised Learning Representation learning, generative models and modern synthesis 3 25
5 · Applied Deep Learning Systems Vision and language applications, deployment and MLOps 3 25
6 · Responsible AI & Capstone Interpretability, fairness, safety and the capstone project 3 24
Total Six modules · eighteen units 18 152

Curriculum position

Where COMP329 fits

COMP329 is the final course in the four-course sequence, building directly on the machine learning foundations established in COMP328.

  1. COMP326 · Data Science Foundations
  2. COMP327 · Generative AI
  3. COMP328 · Machine Learning
  4. COMP329 · Advanced ML & Deep Learning

Learning outcomes

What you will be able to do

On successful completion of COMP329 you will be able to design, implement and critically evaluate advanced machine learning and deep learning systems.

Learning theory & optimisation

  • Explain how gradient-based optimisation trains large models.
  • Apply regularisation and generalisation techniques deliberately.
  • Select evaluation methods appropriate to the problem and data.

Deep architectures

  • Implement neural networks from first principles.
  • Design and train convolutional and recurrent architectures.
  • Diagnose and remedy training pathologies such as vanishing gradients.

Transformers & transfer learning

  • Explain attention and the transformer architecture.
  • Fine-tune pretrained models for new tasks.
  • Choose between training from scratch and transfer learning.

Generative & unsupervised methods

  • Apply representation learning to unlabelled data.
  • Compare autoencoders, GANs, VAEs and diffusion models.
  • Evaluate generative output both quantitatively and critically.

Applied deep learning

  • Build end-to-end pipelines for vision and language tasks.
  • Deploy and monitor models in a production setting.
  • Manage data, compute and reproducibility constraints.

Responsible advanced AI

  • Interpret model behaviour and communicate uncertainty.
  • Assess fairness, robustness and safety risks.
  • Document and justify design decisions professionally.

Curriculum

Six modules, eighteen units

Each unit is delivered as a sequence of tutorial pages: theory, worked derivations, PyTorch walkthroughs, GPU lab activities and a knowledge check.

How it works

A consistent rhythm for every unit

Each unit follows the same four-part structure, so you always know what is expected and how to prepare for assessment.

  1. Study the theory

    Derivations and architecture diagrams explain why a method works, not just how to call it.

  2. Implement it

    Build the model in NumPy first, then reproduce it in PyTorch so the framework holds no mysteries.

  3. Train and evaluate

    Run GPU lab experiments, tune hyperparameters and interpret the results critically.

  4. Check your understanding

    Finish with self-check questions, a unit quiz and a short reflective summary.

Assessment

How your work is assessed

Assessment is weighted towards implementation and the capstone. Five assignments build progressively towards the final project.

35%

Five assignments

Optimisation, network implementation, transformers, generative models and deployment.

30%

Capstone project

A complete deep learning system, from problem definition to evaluated deployment.

15%

Final exam

Cumulative, with an emphasis on architecture reasoning and critical evaluation.

10%

Midterm

Modules 1–3: optimisation, deep networks and sequence models.

10%

Unit quizzes

Eighteen short online quizzes, one per unit, with unlimited attempts.

Weightings are indicative and confirmed in the course syllabus.

  • Assignment 1 Optimisation and Regularisation — implement and compare training strategies Brief
  • Assignment 2 Neural Network Implementation — build and train a network from first principles Brief
  • Assignment 3 Transformers and Transfer Learning — fine-tune a pretrained model Brief
  • Assignment 4 Generative Modelling — train and critically evaluate a generative model Brief
  • Assignment 5 Deployment Project — package, serve and monitor a trained model Brief

Capstone

An end-to-end deep learning system

The capstone runs across the second half of the course. You take a real problem from definition through to a trained, evaluated and documented deep learning artefact, supported by twelve structured phases.

What you submit

  • Project proposal and problem framing
  • Dataset and compute plan
  • Model implementation and training notebook
  • Evaluation report including baselines and ablations
  • Deployed or packaged system
  • Final written report and oral presentation

Portfolio ready

A trained model, reproducible training code and an honest evaluation report together make a strong technical portfolio piece for graduate study or industry roles.

Baselines are mandatory

Every capstone must compare against at least one simple baseline. A complex model that is not shown to outperform a trivial one is not a successful project.

  1. Problem IdentificationDefine a task where learning from data is genuinely justified.
  2. Stakeholder AnalysisIdentify who uses the system and what failure would cost them.
  3. Dataset SelectionSource, document and assess data suitability and licensing.
  4. Data PipelineBuild reproducible loading, splitting and augmentation.
  5. Baseline ImplementationEstablish a simple benchmark before anything complex.
  6. Architecture DesignChoose and justify an architecture for the task.
  7. Training and TuningTrain, monitor and tune within your compute budget.
  8. Evaluation and AblationMeasure performance rigorously and test your design choices.
  9. InterpretationExplain what the model learned and where it fails.
  10. Responsible AI ReviewAssess fairness, robustness and misuse risk.
  11. DeploymentPackage and serve the model with monitoring in place.
  12. Report and PresentationDocument and defend the full system.

Tools & technology

The modern deep learning stack

All tools are free and open source. Laboratory sessions run on shared GPU workstations, and every assignment is completable on free cloud notebook tiers.

Python 3 The language for the entire course.
PyTorch The primary framework for building and training networks.
TensorFlow / Keras An alternative framework, used for comparison and deployment.
scikit-learn Classical baselines, metrics and preprocessing utilities.
Hugging Face Pretrained transformers, datasets and fine-tuning workflows.
Jupyter & GPU Notebook environment with CUDA acceleration for training labs.

Questions

Frequently asked questions

What mathematics do I need before starting?

Comfort with vectors and matrices, partial derivatives and the chain rule, and basic probability. The course reviews the optimisation mathematics it relies on, but it does assume the calculus and linear algebra covered in earlier years.

Do I need my own GPU?

No. Laboratory sessions run on shared GPU workstations, and every assignment is designed to fit within the free tiers of cloud notebook providers. You will learn to work within realistic compute budgets — which is itself an important professional skill.

Should I use PyTorch or TensorFlow?

The course teaches PyTorch as its primary framework because of its clarity and research adoption. TensorFlow and Keras are introduced for comparison and for deployment scenarios. The concepts transfer directly between them.

How does this differ from COMP328?

COMP328 covers machine learning fundamentals: regression, classification, decision trees, ensembles and the core evaluation framework. COMP329 assumes all of that and moves into deep architectures, representation learning, generative models and production deployment.

How much time should I expect to spend each week?

Plan for roughly 12–14 hours per week. Model training adds wall-clock time that you cannot compress, so good time management and early experimentation matter more here than in most courses.

Is the capstone dataset provided?

You may choose your own dataset or select from a curated list of approved sources. Either way, you must document provenance, licensing and any preprocessing decisions as part of the submission.

Ready to build advanced learning systems?

Begin with Module 1, Unit 1 — the optimisation and gradient methods that underpin everything that follows in deep learning.

Start Unit 1 Download syllabus
👤