Models & Architecture
Convolutional Neural Network
CNNA network design built for images, which scans for small visual patterns and builds them up into recognizable objects.
A CNN processes images by sliding small filters across them to detect features like edges and textures, then combining those into higher-level shapes layer by layer. This structure makes it efficient and effective at vision tasks, and CNNs drove the deep learning boom in image recognition. Transformers now rival them on many vision problems, but CNNs remain widely used and easy to deploy.
Reference: Wikipedia: Convolutional Neural Network
Related terms
Computer Vision
The field of AI that lets computers interpret images and video, from recognizing objects to reading documents.
Deep Learning
Machine learning built on large neural networks with many layers, which is what powers most recent AI breakthroughs.
Neural Network
A model loosely inspired by the brain, built from layers of simple units that each pass signals to the next.
Recurrent Neural Network
An older network design for sequences like text or audio, which processes one step at a time while carrying a memory forward.