Showing 2025Show all
2 papers · 1 filter
cs.LG2025
Floating-Point Neural Networks Are Provably Robust Universal Approximators
Geonho Hwang, Wonyeol Lee, Yeachan Park +2
The classical universal approximation (UA) theorem for neural networks establishes mild conditions under which a feedforward neural network can approximate a continuous function $f…
cs.LG2025
Minimum width for universal approximation using squashable activation functions
Jonghyun Shin, Namjun Kim, Geonho Hwang +1
The exact minimum width that allows for universal approximation of unbounded-depth networks is known only for ReLU and its variants. In this work, we study the minimum width of net…