No Fine-Tuning, No Cry: Robust SVD for Compressing Deep Networks

A common technique for compressing a neural network is to compute the k-rank [Formula: see text] approximation [Formula: see text] of the matrix [Formula: see text] via SVD that corresponds to a fully connected layer (or embedding layer). Here, d is the number of input neurons in the layer, n is the...

Descripción completa

Detalles Bibliográficos
Autores principales: Tukan, Murad, Maalouf, Alaa, Weksler, Matan, Feldman, Dan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2021
Materias:
Article
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8402276/
https://www.ncbi.nlm.nih.gov/pubmed/34451040
http://dx.doi.org/10.3390/s21165599

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8402276/
https://www.ncbi.nlm.nih.gov/pubmed/34451040
http://dx.doi.org/10.3390/s21165599

Ejemplares similares