Compact Neural Architecture Designs by Tensor Representations

We propose a framework of tensorial neural networks (TNNs) extending existing linear layers on low-order tensors to multilinear operations on higher-order tensors. TNNs have three advantages over existing networks: First, TNNs naturally apply to higher-order data without flattening, which preserves...

Descripción completa

Detalles Bibliográficos
Autores principales: Su, Jiahao, Li, Jingling, Liu, Xiaoyu, Ranadive, Teresa, Coley, Christopher, Tuan, Tai-Ching, Huang, Furong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Frontiers Media S.A. 2022
Materias:
Artificial Intelligence
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8959219/
https://www.ncbi.nlm.nih.gov/pubmed/35355829
http://dx.doi.org/10.3389/frai.2022.728761

Internet

https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8959219/
https://www.ncbi.nlm.nih.gov/pubmed/35355829
http://dx.doi.org/10.3389/frai.2022.728761

Ejemplares similares