Clemens Kinn

Fast approximation and learning of binary classification tasks in o-minimal structures using ReLU neural networks

It is proved that characteristic functions of traceable subsets of traceable subsets of $[-1/2,1/2]^n$ can be approximated in L^p to accuracy $\varepsilon>0$ by ReLU neural networks of size $\mathcal{O}(\varepsilon^{-p(n-1)/m})$, with depth independent of $\varepsilon$ and polynomially bounded weights.