Learn AI · Level 2 · How AI works · step 8 of 18 · word 1 of 2
What is a convolutional neural network (CNN)?
A convolutional neural network is a kind of neural network built for images. It scans a picture in small patches, finding edges first, then shapes, then whole objects.
In plain English
A CNN looks at an image the way you might search a page with a magnifying glass, one small patch at a time. Early layers spot simple things like edges and colours. Later layers combine them into eyes, wheels or letters, and finally into “cat” or “stop sign”.
An example
In 2012, a CNN called AlexNet won the ImageNet image recognition contest with an error rate of 15.3%, against 26.2% for the next best entry. That leap, powered by GPUs, started the deep learning boom.
Watch out
CNNs still power face unlock, medical scans and factory checks, often on phones. For the biggest image models, transformers have taken over. See one at work in the CNN Explainer in our AI playground.
Learn AI path · Level 2 · How AI works · step 8 of 18
Next wordRecurrent neural network (RNN) →See all of level 2