What is … the difference between deep learning and machine learning?

About this video

When talking about artificial intelligence (AI), deep learning and machine learning are invariably mentioned in the same breath. But what do they mean? Are they same thing? Are they different? In this video, we explain what machine learning and deep learning mean, and how they fit into the AI family.

If you want to learn more about building AI apps, check out the tutorials, code patterns, datasets, models and more on the IBM Developer Artificial Intelligence hub, the Deep learning hub, and the Machine learning hub

Check out more videos in this series:

Transcript of this video

Hello, I’m Sean, here to answer another “What is” question.

This time we’re answering the question, “what is the difference between Machine Learning and Deep Learning?””

With the increasing use of AI in our everyday lives, you may have noticed the terms machine learning and deep learning being used quite a bit sometimes interchangeably. So, is there a difference between Machine Learning and Deep Learning, and if so what is it?

The first thing to understand is that both Machine Learning and Deep learning are both types of AI, and that deep learning is a type of machine learning. So deep learning is a sub-type of machine learning which is itself a sub-type of artificial intelligence. The difference between these two types of AI that’s usually brought up is in the kind of data that’s presented to the AI.

Typically, a machine learning approach will require structured data, that is, data which contains labels for the things you want to identify. So, if I had a bunch of images of cats and mice, a person would need to sit down and label each image as either a cat or a mouse so that the machine learning algorithm could learn the difference between those examples.

Now Deep Learning is a little bit different. If I had the same data set, but didn’t label any of the images, the deep learning algorithm would work to figure out the differences between the two CATegories and group them together.

So even though it wouldn’t explicitly know that one thing is a cat or a mouse, it would still be able to say “I think it’s this thing or that thing.”