Convolution OperationsConvolution is the central operation in convolutional neural networks.
Pooling LayersPooling is a downsampling operation used in convolutional neural networks.
Feature MapsA feature map is the spatial output produced by a convolutional filter. In a convolutional neural network, each output channel can be read as a map of where a learned feature appears in the input.
Padding and StridePadding and stride control the spatial size of convolutional feature maps.
CNN ArchitecturesA convolutional neural network architecture defines how convolutional layers, activation functions, normalization layers, pooling layers, residual paths, and classifier heads are arranged.
Residual NetworksResidual networks are convolutional networks built from blocks with skip connections.
Efficient ConvolutionsEfficient convolutions reduce computation, memory use, or latency while preserving useful spatial modeling.