Convolutional Neural Network (CNN)

A convolutional neural network (CNN) is a deep learning (DL) architecture designed for grid-structured data such as images and video, using convolutional filters to learn local spatial features.

By stacking layers and using pooling or strided operations, CNNs build higher-level representations from lower-level patterns. They have driven major advances in computer vision tasks including image classification, object detection, and semantic segmentation.

Notable CNN architectures include LeNet, AlexNet, VGG, ResNet, and EfficientNet. Despite the rise of Vision Transformers, CNNs remain widely used for their efficiency and strong performance across many applications.