AI RESEARCH

Region Seeding via Pre-Activation Regularization: A Geometric View from Piecewise Affine Nerual Networks

arXiv CS.LG

ArXi:2605.06300v1 Announce Type: new Deep networks with continuous piecewise affine activations induce polyhedral partitions of the input space, making the number of realized affine regions a natural measure of expressive capacity and a key determinant of how well the model can approximate nonlinear target functions. In practice, standard