Eroxl's NotesGraph
Kernel (Convolution)

Kernels are square matricies of weights with dimensions defined by the user. A Kernel is used in the convolutional layer in a convolutional neural network to scan over the input image in order to generate an output

Kernel Size

The kernel size controls how large the square matrix that the kernel uses.

101010101010101010101010101010101010000000000000000000121000-1-2-1InputKernelOutput000040404040404040400000

Example of the final iteration of the convolution performed with a kernel size of

101010101010101010101010101010101010000000000000000000InputKernel122100000000-1-2-2-1Output606060606060606060

Example of the final iteration of the convolution performed with a kernel size of