Cargando…
Overparameterized neural networks implement associative memory
Identifying computational mechanisms for memorization and retrieval of data is a long-standing problem at the intersection of machine learning and neuroscience. Our main finding is that standard overparameterized deep neural networks trained using standard optimization methods implement such a mecha...
Autores principales: | Radhakrishnan, Adityanarayanan, Belkin, Mikhail, Uhler, Caroline |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
National Academy of Sciences
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7959487/ https://www.ncbi.nlm.nih.gov/pubmed/33067397 http://dx.doi.org/10.1073/pnas.2005013117 |
Ejemplares similares
-
Wide and deep neural networks achieve consistency for classification
por: Radhakrishnan, Adityanarayanan, et al.
Publicado: (2023) -
Simple, fast, and flexible framework for matrix completion with infinite width neural networks
por: Radhakrishnan, Adityanarayanan, et al.
Publicado: (2022) -
Transfer Learning with Kernel Methods
por: Radhakrishnan, Adityanarayanan, et al.
Publicado: (2023) -
Causal network models of SARS-CoV-2 expression and aging to identify candidates for drug repurposing
por: Belyaeva, Anastasiya, et al.
Publicado: (2021) -
Machine Learning for Nuclear Mechano-Morphometric Biomarkers in Cancer Diagnosis
por: Radhakrishnan, Adityanarayanan, et al.
Publicado: (2017)