A convolutional layer is a layer that unlike dense layers operates on a small section of its inputs at a time. It does this through convolving the kernel.md) over the top of its inputs, this is where it gets its name of the convolutional layer.
The kernel size controls how large the square matrix that the kernel uses.
Example of the final iteration of the convolution performed with a kernel size of
Example of the final iteration of the convolution performed with a kernel size of
The stride controls how the offset of the kernel.md) changes after each convolution iteration.
Example of two iterations of the convolution performed with a step size of
Example of two iterations of the convolution performed with a step size of
A single convolutional layer can be written as a convolution between two matricies