Integrating geometries of ReLU feedforward neural networks

This paper investigates the integration of multiple geometries present within a ReLU-based neural network. A ReLU neural network determines a piecewise affine linear continuous map, M, from an input space ℝm to an output space ℝn. The piecewise behavior corresponds to a polyhedral decomposition of ℝ...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Yajing Liu, Turgay Caglar, Christopher Peterson, Michael Kirby
Format:	Artigo
Sprog:	Inglês
Udgivet:	Frontiers Media S.A. 2023-11-01
Serier:	Frontiers in Big Data
Fag:	ReLU feedforward neural networks binary vectors polyhedral decomposition geometries Chebyshev center Hamming distance
Online adgang:	https://www.frontiersin.org/articles/10.3389/fdata.2023.1274831/full
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!