Cargando…
Learning on tree architectures outperforms a convolutional feedforward network
Advanced deep learning architectures consist of tens of fully connected and convolutional hidden layers, currently extended to hundreds, are far from their biological realization. Their implausible biological dynamics relies on changing a weight in a non-local manner, as the number of routes between...
Autores principales: | Meir, Yuval, Ben-Noam, Itamar, Tzach, Yarden, Hodassman, Shiri, Kanter, Ido |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Nature Publishing Group UK
2023
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9886946/ https://www.ncbi.nlm.nih.gov/pubmed/36717568 http://dx.doi.org/10.1038/s41598-023-27986-6 |
Ejemplares similares
-
Efficient shallow learning as an alternative to deep learning
por: Meir, Yuval, et al.
Publicado: (2023) -
Brain experiments imply adaptation mechanisms which outperform common AI learning algorithms
por: Sardi, Shira, et al.
Publicado: (2020) -
Publisher Correction: Brain experiments imply adaptation mechanisms which outperform common AI learning algorithms
por: Sardi, Shira, et al.
Publicado: (2020) -
Power-law scaling to assist with key challenges in artificial intelligence
por: Meir, Yuval, et al.
Publicado: (2020) -
Brain inspired neuronal silencing mechanism to enable reliable sequence identification
por: Hodassman, Shiri, et al.
Publicado: (2022)