CNN基础(3)

Convolutional Neural Networks (CNNs / ConvNets)

1. Local Connectivity(==local receptive fields==).
2. Parameter Sharing(==shared weights==).
3. ==sub-sampling==

Convolutional Layer

Local Connectivity

Spatial arrangement

depth
stride
zero-padding

Parameter Sharing

Pooling Layer

Normalization Layer

Fully-Connected Layer

Neurons in a fully connected layer have full connections to all activations in the previous layer, as seen in regular Neural Networks. Their activations can hence be computed with a matrix multiplication followed by a bias offset.