A Convolutional Neural Network (CNN) is a deep learning architecture especially effective for processing grid-like data such as images and time series. It comprises multiple layers: convolutional layers that apply learnable filters to extract local features; pooling layers that downsample the feature maps to reduce computational load and control overfitting; and fully connected layers that perform high-level reasoning. CNNs leverage spatial hierarchies via shared weights and local connectivity, capturing translation-invariant patterns such as edges, textures, and shapes. They have revolutionized computer vision tasks like image classification, object detection, and semantic segmentation, and are increasingly applied in audio and natural language processing domains.