AI

What you will learn

• Explain what data is and the difference between features, labels, inputs and outputs.
• Describe in plain language what supervised and unsupervised learning are trying to do.
• Understand basic ideas like training, validation and testing at a high level.
• Recognise common data problems such as bias, noise and leakage.
• Describe how common model families such as linear models, trees and simple neural networks behave.
• Explain important evaluation metrics in context, such as accuracy, precision, recall and F1, and when they are appropriate.

Who this course is for

• People from non technical backgrounds who want to understand AI properly.
• Students and early career professionals who need to connect maths, models and real world use cases.
• Teams and lecturers who want ready made explanations, diagrams and tools to use in classes.

Prerequisites: None.