Skip to content
Know.itKnow.it
Create an animated lesson
On request

This article is free to read. Creating a lesson uses your daily or stored credits; review the language and settings before starting.

What is deep learning?

TechnologyLesson on requestFree to read

Quick answer

Deep learning is a type of machine learning that uses neural networks with many layers to learn patterns directly from data. It powers modern AI — from image recognition and speech to chatbots — by automatically discovering features instead of being hand-programmed.

Key things to understand

  1. It's a branch of machine learning built on multi-layered neural networks.
  2. Each layer learns increasingly abstract features from the data.
  3. It needs lots of data and computing power to train well.
  4. It drives image recognition, speech, translation, and chatbots.

People also ask

What's the difference between machine learning and deep learning?
Deep learning is a subset of machine learning that uses many-layered neural networks to learn features automatically.
Why is it called 'deep' learning?
Because the neural networks have many stacked layers — the 'depth' that lets them learn complex patterns.
What is deep learning used for?
Image and speech recognition, language translation, recommendation systems, self-driving cars, and chatbots.

Part of the guide: How AI Works →