Deep Learning & Neural Networks
Unlocking the black box of multi-layered artificial intelligence.
Modules4 Sessions
Duration16 weeks
Outcomes5 Skills
Course Overview
Welcome to the frontier. In this phase, we explore the bio-inspired architectures that allow machines to see, hear, and understand. You will build neural networks from the ground up, starting with single perceptrons and moving to complex Convolutional Neural Networks (CNNs) for image recognition and Recurrent Neural Networks (RNNs) for sequential data. You'll learn how backpropagation allows models to learn from their mistakes and how deep architectures can extract features without human supervision.
Tools & Technologies
PyTorchTensorFlowCUDACNN Architectures
Curriculum
4 ModulesWhat You'll Learn
- Build multi-layer perceptrons from scratch using PyTorch
- Design CNNs for high-accuracy image classification
- Implement backpropagation and gradient descent manually
- Optimise deep networks with dropout and batch normalisation
- Execute architectural transfers learning on pre-trained models
Prerequisites
- Applied Machine Learning