Cargando…
A law of data separation in deep learning
While deep learning has enabled significant advances in many areas of science, its black-box nature hinders architecture design for future artificial intelligence applications and interpretation for high-stakes decision-makings. We addressed this issue by studying the fundamental question of how dee...
Autores principales: | He, Hangfeng, Su, Weijie J. |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
National Academy of Sciences
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10483613/ https://www.ncbi.nlm.nih.gov/pubmed/37639604 http://dx.doi.org/10.1073/pnas.2221704120 |
Ejemplares similares
-
Exploring deep neural networks via layer-peeled model: Minority collapse in imbalanced training
por: Fang, Cong, et al.
Publicado: (2021) -
On conservation laws in quantum mechanics
por: Aharonov, Yakir, et al.
Publicado: (2021) -
Conservation laws and the foundations of quantum mechanics
por: Aharonov, Yakir, et al.
Publicado: (2023) -
Machine learning enables interpretable discovery of innovative polymers for gas separation membranes
por: Yang, Jason, et al.
Publicado: (2022) -
Deep learning predicts path-dependent plasticity
por: Mozaffar, M., et al.
Publicado: (2019)