from Suzuki, Daiji - Mathematics of Deep Learning
universal approximation
Arbitrary continuous functions can be approximated by sigmoidal [activation functions
This page is auto-translated from /nishio/万能近似 using DeepL. If you looks something interesting but the auto-translated English is not good enough to understand it, feel free to let me know at @nishio_en. I’m very happy to spread my thought to non-Japanese readers.