In the convolutional layer, each neuron only collects some information. This effectively reduces the memory required.

The convolutional layer uses parameter sharing so that features at different positions share the same group of parameters. This reduces the number of network parameters required but reduces the expression capabilities of models.

A stride in the convolutional layer can control the spatial resolution of the output feature map. A larger stride indicates a smaller output feature map and simpler calculation.

The convolutional layer slides over the input feature map using a convolution kernel of a fixed size to extract local features without explicitly defining their features.