Cargando…
Neurons with dendrites can perform linearly separable computations with low resolution synaptic weights
In theory, neurons modelled as single layer perceptrons can implement all linearly separable computations. In practice, however, these computations may require arbitrarily precise synaptic weights. This is a strong constraint since both biological neurons and their artificial counterparts have to co...
Autores principales: | Cazé, Romain D., Stimberg, Marcel |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
F1000 Research Limited
2021
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7848858/ https://www.ncbi.nlm.nih.gov/pubmed/33564396 http://dx.doi.org/10.12688/f1000research.26486.3 |
Ejemplares similares
-
All neurons can perform linearly non-separable computations
por: Cazé, Romain D.
Publicado: (2022) -
Passive Dendrites Enable Single Neurons to Compute Linearly Non-separable Functions
por: Cazé, Romain Daniel, et al.
Publicado: (2013) -
Contribution of sublinear and supralinear dendritic integration to neuronal computations
por: Tran-Van-Minh, Alexandra, et al.
Publicado: (2015) -
A robust model of sensory tuning using dendritic non-linearities
por: Cazé, Romain D, et al.
Publicado: (2015) -
Dynamical Characteristics of Recurrent Neuronal Networks Are Robust Against Low Synaptic Weight Resolution
por: Dasbach, Stefan, et al.
Publicado: (2021)