Chapter 14 sections from Deep Learning with PyTorch.
7 items
Convolution is the central operation in convolutional neural networks.
Pooling is a downsampling operation used in convolutional neural networks.
A 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 stride control the spatial size of convolutional feature maps.
A convolutional neural network architecture defines how convolutional layers, activation functions, normalization layers, pooling layers, residual paths, and classifier heads are arranged.
Residual networks are convolutional networks built from blocks with skip connections.
Efficient convolutions reduce computation, memory use, or latency while preserving useful spatial modeling.