Convolutional Neural Network
A neural network architecture specialized for processing grid-like data such as images using convolutional filters.
Convolutional Neural Networks (CNNs) are the backbone of classical computer vision. They use convolutional layers that slide small filters across the input, detecting local patterns like edges, textures, and shapes. Early layers capture simple features; deeper layers build up to complex objects.
Famous CNN architectures include AlexNet, VGG, ResNet, and EfficientNet. They dominated vision tasks throughout the 2010s before transformers (Vision Transformers) became competitive.
CNNs remain essential for many vision tasks due to their efficiency and inductive bias for spatial data. They're used in image classification, object detection, segmentation, and medical imaging.