It seems that complexity should regard the combinatorial nature of the space prior to classifying outputs. If a k-by-k array of pixels, each pixel on or off, is to be classified into one out of z image-tags, complexity is greater for classifiers which make jagged or discontinuous associations, compared to a classifier which simply segments according to vertical or horizontal lines. How is the complexity of pixel-to-classifier expressed in your equation?

Written by

Easily distracted mathematician

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store