Voltage-dependent synaptic plasticity: ...
Type de document :
Compte-rendu et recension critique d'ouvrage
Titre :
Voltage-dependent synaptic plasticity: Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential
Auteur(s) :
Garg, Nikhil [Auteur]
Institut Interdisciplinaire d'Innovation Technologique [Sherbrooke] [3IT]
Laboratoire Nanotechnologies et Nanosystèmes [Sherbrooke] [LN2]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Nanostructures, nanoComponents & Molecules - IEMN [NCM - IEMN]
International Computer Science Institute [Berkeley] [ICSI]
Balafrej, Ismael [Auteur]
Laboratoire Nanotechnologies et Nanosystèmes [Sherbrooke] [LN2]
Institut Interdisciplinaire d'Innovation Technologique [Sherbrooke] [3IT]
Stewart, Terrence [Auteur]
University of Waterloo [Waterloo]
Portal, Jean-Michel [Auteur]
Institut des Matériaux, de Microélectronique et des Nanosciences de Provence [IM2NP]
Bocquet, Marc [Auteur]
Institut des Matériaux, de Microélectronique et des Nanosciences de Provence [IM2NP]
Querlioz, D. [Auteur]
Centre de Nanosciences et de Nanotechnologies [C2N]
Drouin, Dominique [Auteur]
Institut Interdisciplinaire d'Innovation Technologique [Sherbrooke] [3IT]
Laboratoire Nanotechnologies et Nanosystèmes [Sherbrooke] [LN2]
Rouat, Jean [Auteur]
Université de Sherbrooke [UdeS]
Beilliard, Yann [Auteur]
Institut Interdisciplinaire d'Innovation Technologique [Sherbrooke] [3IT]
Laboratoire Nanotechnologies et Nanosystèmes [Sherbrooke] [LN2]
Alibart, Fabien [Auteur]
Laboratoire Nanotechnologies et Nanosystèmes [Sherbrooke] [LN2]
Nanostructures, nanoComponents & Molecules - IEMN [NCM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Institut Interdisciplinaire d'Innovation Technologique [Sherbrooke] [3IT]
Laboratoire Nanotechnologies et Nanosystèmes [Sherbrooke] [LN2]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Nanostructures, nanoComponents & Molecules - IEMN [NCM - IEMN]
International Computer Science Institute [Berkeley] [ICSI]
Balafrej, Ismael [Auteur]
Laboratoire Nanotechnologies et Nanosystèmes [Sherbrooke] [LN2]
Institut Interdisciplinaire d'Innovation Technologique [Sherbrooke] [3IT]
Stewart, Terrence [Auteur]
University of Waterloo [Waterloo]
Portal, Jean-Michel [Auteur]
Institut des Matériaux, de Microélectronique et des Nanosciences de Provence [IM2NP]
Bocquet, Marc [Auteur]
Institut des Matériaux, de Microélectronique et des Nanosciences de Provence [IM2NP]
Querlioz, D. [Auteur]
Centre de Nanosciences et de Nanotechnologies [C2N]
Drouin, Dominique [Auteur]
Institut Interdisciplinaire d'Innovation Technologique [Sherbrooke] [3IT]
Laboratoire Nanotechnologies et Nanosystèmes [Sherbrooke] [LN2]
Rouat, Jean [Auteur]
Université de Sherbrooke [UdeS]
Beilliard, Yann [Auteur]
Institut Interdisciplinaire d'Innovation Technologique [Sherbrooke] [3IT]
Laboratoire Nanotechnologies et Nanosystèmes [Sherbrooke] [LN2]
Alibart, Fabien [Auteur]
Laboratoire Nanotechnologies et Nanosystèmes [Sherbrooke] [LN2]
Nanostructures, nanoComponents & Molecules - IEMN [NCM - IEMN]
Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 [IEMN]
Titre de la revue :
Frontiers in Neuroscience
Pagination :
983950, 12 pages
Éditeur :
Frontiers
Date de publication :
2022-10-21
ISSN :
1662-4548
Mot(s)-clé(s) en anglais :
spiking neural networks
Hebbian plasticity
STDP
unsupervised learning
synaptic plasticity
modified national institute of standards and technology database (MNIST)
Hebbian plasticity
STDP
unsupervised learning
synaptic plasticity
modified national institute of standards and technology database (MNIST)
Discipline(s) HAL :
Sciences de l'ingénieur [physics]
Résumé en anglais : [en]
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 ...
Lire la suite >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.Lire moins >
Lire la suite >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.Lire moins >
Langue :
Anglais
Vulgarisation :
Non
Source :
Fichiers
- https://hal.archives-ouvertes.fr/hal-03834905/document
- Accès libre
- Accéder au document
- http://arxiv.org/pdf/2203.11022
- Accès libre
- Accéder au document
- document
- Accès libre
- Accéder au document
- Garg_fnins-16-9839503.pdf
- Accès libre
- Accéder au document
- 2203.11022
- Accès libre
- Accéder au document