[xpe]

splines, yes.

I'm not seeing decision trees, though. Am I missing something?

> "KANs’ nodes simply sum incoming signals without applying any non-linearities." (page 2 of the PDF)

[cbsmith]

I definitely think I'm projecting and maybe seeing things that aren't there. If you replaced splines with linear weights, it kind of looks like a decision tree to me.

[xpe]

If it were me, I would let go of that association, unless you find value in it.