Cargando…
A Deep Non-negative Matrix Factorization Model for Big Data Representation Learning
Nowadays, deep representations have been attracting much attention owing to the great performance in various tasks. However, the interpretability of deep representations poses a vast challenge on real-world applications. To alleviate the challenge, a deep matrix factorization method with non-negativ...
Autores principales: | Chen, Zhikui, Jin, Shan, Liu, Runze, Zhang, Jianing |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8329448/ https://www.ncbi.nlm.nih.gov/pubmed/34354579 http://dx.doi.org/10.3389/fnbot.2021.701194 |
Ejemplares similares
-
Bio-inspired Analysis of Deep Learning on Not-So-Big Data Using Data-Prototypes
por: Drumond, Thalita F., et al.
Publicado: (2019) -
JDSNMF: Joint Deep Semi-Non-Negative Matrix Factorization for Learning Integrative Representation of Molecular Signals in Alzheimer’s Disease
por: Moon, Sehwan, et al.
Publicado: (2021) -
Automatic Analysis of EEGs Using Big Data and Hybrid Deep Learning Architectures
por: Golmohammadi, Meysam, et al.
Publicado: (2019) -
Co-sparse Non-negative Matrix Factorization
por: Wu, Fan, et al.
Publicado: (2022) -
Transferred Subspace Learning Based on Non-negative Matrix Factorization for EEG Signal Classification
por: Dong, Aimei, et al.
Publicado: (2021)