A type of deep learning architecture that excels at processing data with a grid-like topology, such as images, and is particularly effective at identifying patterns in images to recognize objects, classes, and categories, but can also classify audio, time-series, and signal data.
A CNN is trained on a large dataset of images of dogs to recognize different breeds. The network learns to identify features such as ear shape, coat color, and body size to correctly classify new images as belonging to a specific breed.