Search Results for author: Gaoxiang Chen

Found 2 papers, 0 papers with code

A General Computational Framework to Measure the Expressiveness of Complex Networks using a Tight Upper Bound of Linear Regions

no code implementations1 Jan 2021 Yutong Xie, Gaoxiang Chen, Quanzheng Li

Inspired by the proof of this upper bound and the framework of matrix computation in \citet{hinz2019framework}, we propose a general computational approach to compute a tight upper bound of regions number for theoretically any network structures (e. g. DNN with all kind of skip connections and residual structures).

A General Computational Framework to Measure the Expressiveness of Complex Networks Using a Tighter Upper Bound of Linear Regions

no code implementations8 Dec 2020 Yutong Xie, Gaoxiang Chen, Quanzheng Li

Inspired by the proof of this upper bound and theframework of matrix computation in Hinz & Van de Geer (2019), we propose ageneral computational approach to compute a tight upper bound of regions numberfor theoretically any network structures (e. g. DNN with all kind of skip connec-tions and residual structures).

Cannot find the paper you are looking for? You can Submit a new open access paper.