Cargando…
Efficient shallow learning as an alternative to deep learning
The realization of complex classification tasks requires training of deep learning (DL) architectures consisting of tens or even hundreds of convolutional and fully connected hidden layers, which is far from the reality of the human brain. According to the DL rationale, the first convolutional layer...
Autores principales: | Meir, Yuval, Tevet, Ofek, Tzach, Yarden, Hodassman, Shiri, Gross, Ronit D., 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/PMC10119101/ https://www.ncbi.nlm.nih.gov/pubmed/37080998 http://dx.doi.org/10.1038/s41598-023-32559-8 |
Ejemplares similares
-
Enhancing the accuracies by performing pooling decisions adjacent to the output layer
por: Meir, Yuval, et al.
Publicado: (2023) -
Learning on tree architectures outperforms a convolutional feedforward network
por: Meir, Yuval, et al.
Publicado: (2023) -
Efficient dendritic learning as an alternative to synaptic plasticity hypothesis
por: Hodassman, Shiri, et al.
Publicado: (2022) -
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)