Showing cs.LGShow all
2 papers · 1 filter
cs.LG2024
Implicit Hypersurface Approximation Capacity in Deep ReLU Networks
Jonatan Vallin, Karl Larsson, Mats G. Larson
We develop a geometric approximation theory for deep feed-forward neural networks with ReLU activations. Given a -dimensional hypersurface in represented as t…
cs.LG2023
The Geometric Structure of Fully-Connected ReLU Layers
Jonatan Vallin, Karl Larsson, Mats G. Larson
We formalize and interpret the geometric structure of -dimensional fully connected ReLU layers in neural networks. The parameters of a ReLU layer induce a natural partition of t…