AIExplainer

What is convolutional neural network?

A type of artificial neural network designed to process data with grid-like topology

Stands for: CNN

A convolutional neural network is a type of artificial intelligence model that is particularly good at recognizing patterns in images, sounds, and other types of data that have a spatial structure. It works by applying filters to small sections of the data, scanning the data in a way that is similar to how the human eye scans a scene.

Imagine trying to recognize a picture of a cat. A convolutional neural network is like a sliding window that moves over the picture, looking at small sections at a time and building up a understanding of the whole image, much like how you might look at different parts of the picture to recognize the cat's ears, eyes, and whiskers.

Google's self-driving cars use convolutional neural networks to recognize and respond to objects on the road, such as pedestrians, other cars, and traffic signals.

Convolutional neural networks are commonly used in image recognition, object detection, and image classification tasks, such as self-driving cars, facial recognition, and medical image analysis.

One common misconception is that convolutional neural networks are only used for image recognition, when in fact they can be applied to any type of data with a spatial structure, such as audio or text data.

The concept of convolutional neural networks was first introduced in the 1980s, but they didn't become widely used until the 2010s, when advances in computing power and large datasets made it possible to train them effectively.

CNN convnet deep convolutional neural network

Three products for different needs — explore what’s relevant to you.