Neurons with dendrites can perform linearly separable computations with low resolution synaptic weights - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue F1000Research Année : 2021

Neurons with dendrites can perform linearly separable computations with low resolution synaptic weights

Résumé

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 cope with limited precision. Here, we explore how non-linear processing in dendrites helps overcome this constraint. We start by finding a class of computations which requires increasing precision with the number of inputs in a perceptron and show that it can be implemented without this constraint in a neuron with sub-linear dendritic subunits. Then, we complement this analytical study by a simulation of a biophysical neuron model with two passive dendrites and a soma, and show that it can implement this computation. This work demonstrates a new role of dendrites in neural computation: by distributing the computation across independent subunits, the same computation can be performed more efficiently with less precise tuning of the synaptic weights. This work not only offers new insight into the importance of dendrites for biological neurons, but also paves the way for new, more efficient architectures of artificial neuromorphic chips.
Fichier principal
Vignette du fichier
Caze_2022_F1000R_Neurons-with-dendrites.pdf (1.52 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : CC BY - Paternité

Dates et versions

hal-03169605 , version 1 (02-05-2024)

Identifiants

Citer

Romain Caze, Marcel Stimberg. Neurons with dendrites can perform linearly separable computations with low resolution synaptic weights. F1000Research, 2021, 9, pp.1174. ⟨10.12688/f1000research.26486.2⟩. ⟨hal-03169605⟩
25 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More