Our Course Catalogue
Structured learning paths from foundations to advanced specialisation
Each course combines theoretical depth with substantial practical projects. All materials receive quarterly updates reflecting the latest developments in the field. Enrolment includes lifetime access to content, instructor support, and our graduate community.
Neural Networks Foundations
Begin your journey into artificial intelligence with a comprehensive exploration of how neural networks learn. This course builds understanding systematically, starting with simple perceptrons and advancing through multilayer architectures, backpropagation algorithms, and regularisation techniques.
- Mathematical foundations made accessible
- Implementation from scratch in Python
- Framework introduction with PyTorch
- Four complete hands-on projects
- 8 weeks of structured content
Deep Learning Intensive
Move beyond fundamentals into the architectures powering modern AI applications. Master convolutional networks for vision tasks, recurrent structures for sequential data, and the attention mechanisms that revolutionised natural language processing. Each architecture is examined theoretically then applied to challenging problems.
- CNN architectures from LeNet to EfficientNet
- Sequence modelling with LSTMs and GRUs
- Attention and self-attention mechanisms
- Transfer learning strategies
- Six substantial projects across domains
- 12 weeks of intensive content
Transformers and Large Language Models
Understand the architecture behind the AI systems capturing global attention. From the original transformer paper through modern large language models, learn how these systems work, why they perform so impressively, and how to adapt them for your applications through fine-tuning and prompt engineering.
- Transformer architecture deep dive
- Pretraining objectives and strategies
- Fine-tuning for downstream tasks
- Prompt engineering techniques
- Responsible deployment considerations
- 10 weeks plus capstone project
MLOps and Deployment
Bridge the gap between model development and production systems. Learn to containerise models, build scalable inference pipelines, implement monitoring for drift detection, and establish workflows that enable rapid iteration without sacrificing reliability.
- Model serialisation and versioning
- Docker and Kubernetes fundamentals
- CI/CD pipelines for ML
- Monitoring and observability
- Cost optimisation strategies
- 8 weeks with production deployment
Computer Vision Masterclass
Specialise in visual intelligence with comprehensive coverage of modern computer vision techniques. From image classification through object detection to generative models, master the methods that enable machines to understand and create visual content.
- Image preprocessing and augmentation
- Object detection architectures
- Semantic and instance segmentation
- GANs and diffusion models
- Video understanding fundamentals
- 10 weeks with portfolio project
Reinforcement Learning
Explore the paradigm that enables agents to learn through interaction with environments. From foundational concepts like Markov decision processes through deep Q-learning to policy gradient methods, understand how to build systems that improve through experience.
- MDP formulation and solutions
- Value-based methods and DQN
- Policy gradient algorithms
- Actor-critic architectures
- Multi-agent considerations
- 10 weeks with simulation projects
Not Sure Where to Start?
If you are new to neural networks, we recommend beginning with the Foundations course. It provides the conceptual grounding that makes advanced topics accessible. Students who skip fundamentals often struggle later; those who invest in foundations accelerate through subsequent courses.
For experienced practitioners seeking specialisation, jump directly into the advanced courses aligned with your interests. Each stands alone while benefiting from familiarity with core concepts.
"I tried learning from YouTube tutorials and textbooks for months without making real progress. Within weeks of starting the Foundations course, concepts that had seemed impossibly abstract became clear and implementable. The structured approach made all the difference."— Rachel T., Software Developer transitioning to ML