Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Expressive Power of Floating-Point Neural Networks with Arbitrary Reduction Orders and Inexact Activation Implementations
Yeachan Park, Geonho Hwang, Wonyeol Lee +1
Most existing expressivity theories for neural networks assume exact real arithmetic, whereas practical neural networks are executed under finite-precision floating-point arithmeti…
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.LG2024
Expressive Power of ReLU and Step Networks under Floating-Point Operations
Yeachan Park, Geonho Hwang, Wonyeol Lee +1
The study of the expressive power of neural networks has investigated the fundamental limits of neural networks. Most existing results assume real-valued inputs and parameters as w…