Neural Networks

About this course

Understand how neural networks learn by examining backpropagation, optimisation, sequence memory and the practical causes of unreliable predictions.

This advanced course is part of the AI & Generative AI school. Work through the curriculum below in a instructor-led / cohort format, with an estimated study time of 30 h.

Course curriculum

• Module 1 — Networks from First Principles
• Module 2 — Backpropagation in Matrix Form
• Module 3 — Initialisation, Normalisation and Residual Connections
• Module 4 — Optimisation Dynamics
• Module 5 — Generalisation and Regularisation
• Module 6 — Recurrent Networks and Sequence Memory
• Module 7 — Neural Networks for Tabular Data
• Module 8 — Uncertainty, Calibration and Debugging

Applied learning

• Case study — The network that would not train: a post-mortem
• Lab 1 — Backpropagation from scratch
• Lab 2 — Training clinic
• Lab 3 — A network ensemble for Harbourline, with uncertainty
• Capstone — A Neural-Network Study

Who this course is for

Technology Professional; Data Professional; Engineer / Architect

Prerequisites

NE-AI-201

Course details

• Course code: NE-AI-302
• Level: Advanced
• Estimated duration: 30 h
• Delivery: Instructor-Led / Cohort