Skip to content
Back to course

12.1 What is Deep Learning?

Deep learning is a branch of machine learning that uses neural networks with many stacked layers to learn directly from raw data. Instead of an engineer hand-crafting the features, each layer learns to transform the data into more useful representations, with later layers building on earlier ones.

A deep network stacks several hidden layers between input and output.

Think of a phone app that recognises Ethiopian coffee beans by photo. Early layers detect edges and colours, middle layers detect shapes like bean curves, and final layers decide the variety — all learned from example photos, not written as rules.

Scenario

You have only 200 labelled images and a simple task. Is deep learning the obvious first choice?

Check your understanding

1/4 · 40 XP

What mainly distinguishes deep learning from classical machine learning?