Voltage-dependent synaptic plasticity: Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Frontiers in Neuroscience Année : 2022

Voltage-dependent synaptic plasticity: Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential

D. Querlioz

Résumé

This study proposes voltage-dependent-synaptic plasticity (VDSP), a novel brain-inspired unsupervised local learning rule for the online implementation of Hebb’s plasticity mechanism on neuromorphic hardware. The proposed VDSP learning rule updates the synaptic conductance on the spike of the postsynaptic neuron only, which reduces by a factor of two the number of updates with respect to standard spike timing dependent plasticity (STDP). This update is dependent on the membrane potential of the presynaptic neuron, which is readily available as part of neuron implementation and hence does not require additional memory for storage. Moreover, the update is also regularized on synaptic weight and prevents explosion or vanishing of weights on repeated stimulation. Rigorous mathematical analysis is performed to draw an equivalence between VDSP and STDP. To validate the system-level performance of VDSP, we train a single-layer spiking neural network (SNN) for the recognition of handwritten digits. We report 85.01 ± 0.76% (Mean ± SD) accuracy for a network of 100 output neurons on the MNIST dataset. The performance improves when scaling the network size (89.93 ± 0.41% for 400 output neurons, 90.56 ± 0.27 for 500 neurons), which validates the applicability of the proposed learning rule for spatial pattern recognition tasks. Future work will consider more complicated tasks. Interestingly, the learning rule better adapts than STDP to the frequency of input signal and does not require hand-tuning of hyperparameters.
Fichier principal
Vignette du fichier
Garg_fnins-16-9839503.pdf (5.63 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03834905 , version 1 (31-10-2022)

Licence

Paternité

Identifiants

Citer

Nikhil Garg, Ismael Balafrej, Terrence Stewart, Jean-Michel Portal, Marc Bocquet, et al.. Voltage-dependent synaptic plasticity: Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential. Frontiers in Neuroscience, 2022, 16, 983950, 12 p. ⟨10.3389/fnins.2022.983950⟩. ⟨hal-03834905⟩
100 Consultations
35 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More