Convolution kernels slide across an input and produce feature maps from nearby values using the same weights at every location. Deeper layers combine local features into larger-scale representations, especially for images, audio, and grids.
A convolutional neural network applies shared local filters to detect spatial or temporal patterns.
Convolution kernels slide across an input and produce feature maps from nearby values using the same weights at every location. Deeper layers combine local features into larger-scale representations, especially for images, audio, and grids.