Convolution

/ˌkɒnvəˈluːʃən/

Convolution: A mathematical operation that slides a filter/kernel over input data to extract features. Convolution computes dot products between the filter and local regions of input. The filter moves with a stride, producing a feature map. Key operation in CNNs for spatial feature extraction.

In italiano: ConvoluzioneLegge III · Come una rete impara dai dati

Convolution computes dot products between the filter and local regions of input. The filter moves with a stride, producing a feature map. Key operation in CNNs for spatial feature extraction.

Examples

  • 2D convolution for images
  • 1D convolution for sequences
  • Edge detection filters