A Convolutional Neural Network (CNN or ConvNet) is a deep learning algorithm specifically designed for processing structured grid data, such as images. It uses a mathematical operation called convolution to filter inputs for useful information. Layers of a CNN learn to detect features like edges, textures, and shapes, hierarchically building up to complex objects.
Inspired by the biological processes in the visual cortex (Hubel and Wiesel, 1962). The modern CNN architecture was pioneered by Yann LeCun in the 1980s (LeNet). The breakthrough moment was the victory of AlexNet in the 2012 ImageNet competition.
CNNs are the gold standard for image classification, object detection, and medical image analysis. They have also been applied to natural language processing and time-series forecasting.