From my limited understanding, CNNs seem to approximate this functionality in image processing tasks, where the convolution layers are akin to the retina extracting info (lines, shapes, etc) and compression (kernel striding and pooling), while the later fully-connected neural network works for categorization or whatnot.

That probably doesn't answer the question of how a bee's eyes work, though.

???

I guess that's true for mammalian eyes, but what about insect eyes? If the bumble brain only hold 200k neurons, how many do their eyes have on board?

~7000 elements per compound eye according to this page:

https://www.google.co.uk/amp/s/brookfieldfarmhoney.wordpress...

That's individual lenses, right? But it says that each lens has its own photoreceptor(s). So that is a multiple of 7000.

So if that's three photo receptors per facet, already each eye is rivaling the neuron count of the brain.