What the course covers.
- Module 1
Neural Network Foundations
Learners begin by understanding the core principles behind neural networks, including perceptrons, activation functions, backpropagation, and optimisation algorithms. This module balances theory with practical exercises, allowing learners to build simple neural networks from scratch, visualise their behaviour, and appreciate the mathematics behind deep learning in a clear, accessible way.
- Module 2
Advanced Architectures
This module explores modern neural network architectures such as convolutional neural networks (CNNs) for image processing, recurrent neural networks (RNNs) for sequential data, and transformers for natural language processing. Learners will implement these models using popular frameworks like TensorFlow and PyTorch, applying them to real-world datasets to gain hands-on experience with complex AI systems.
- Module 3
Model Training & Optimisation
Focusing on making models work in practice, this module covers data preprocessing, loss functions, regularisation, hyperparameter tuning, and evaluation metrics. Learners also learn to detect and prevent overfitting, accelerate training with GPU optimisation, and implement strategies to improve model performance and reliability in production environments.
