# Convolutional filter

> One of the two actors in a convolutional operation. (The other actor is a slice of an input matrix.) A convolutional filter is a matrix having the same rank as the input matrix, but a smaller shape. For example, given a 28x28 input matrix, the filter could be any 2D matrix smaller than 28x28.[^1]

One of the two actors in a [convolutional operation](https://wiki.g15e.com/pages/Convolutional%20operation.txt). (The other actor is a slice of an input matrix.) A convolutional filter is a matrix having the same rank as the input matrix, but a smaller shape. For example, given a 28x28 input matrix, the filter could be any 2D matrix smaller than 28x28.[^1]

In photographic manipulation, all the cells in a convolutional filter are typically set to a constant pattern of ones and zeroes. In machine learning, convolutional filters are typically seeded with random numbers and then the network [trains](https://wiki.g15e.com/pages/Training%20(machine%20learning.txt)) the ideal values.[^1]

## Footnotes

[^1]: