دورية أكاديمية
Voltage-dependent synaptic plasticity: Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential
| العنوان: | Voltage-dependent synaptic plasticity: Unsupervised probabilistic Hebbian plasticity rule based on neurons membrane potential |
|---|---|
| المؤلفون: | Garg, Nikhil, Balafrej, Ismael, Stewart, Terrence, Portal, Jean-Michel, Bocquet, Marc, Querlioz, D., Drouin, Dominique, Rouat, Jean, Beilliard, Yann, Alibart, Fabien |
| المساهمون: | International Computer Science Institute Berkeley (ICSI), International Computer Science Institute, Nanostructures, nanoComponents & Molecules - IEMN (NCM - IEMN), Institut d’Électronique, de Microélectronique et de Nanotechnologie - UMR 8520 (IEMN), Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), Université catholique de Lille (UCL)-Université catholique de Lille (UCL)-Centrale Lille-Université de Lille-Centre National de la Recherche Scientifique (CNRS)-Université Polytechnique Hauts-de-France (UPHF)-JUNIA (JUNIA), Université catholique de Lille (UCL)-Université catholique de Lille (UCL), Laboratoire Nanotechnologies et Nanosystèmes Sherbrooke (LN2), Université de Sherbrooke (UdeS)-École Centrale de Lyon (ECL), Université de Lyon-Université de Lyon-École Supérieure de Chimie Physique Électronique de Lyon (CPE)-Institut National des Sciences Appliquées de Lyon (INSA Lyon), Université de Lyon-Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA), Institut Interdisciplinaire d'Innovation Technologique Sherbrooke (3IT), Université de Sherbrooke (UdeS), University of Waterloo Waterloo, Institut des Matériaux, de Microélectronique et des Nanosciences de Provence (IM2NP), Aix Marseille Université (AMU)-Université de Toulon (UTLN)-Centre National de la Recherche Scientifique (CNRS), Centre de Nanosciences et de Nanotechnologies (C2N), Université Paris-Saclay-Centre National de la Recherche Scientifique (CNRS), We acknowledged financial supports from the EU: ERC-2017-COG project IONOS (# GA 773228) and CHIST-ERA UNICO project. This work was also supported by the Natural Sciences and Engineering Research Council of Canada (NSERC) (No. 559,730) and Fond de Recherche du Québec Nature etTechnologies (FRQNT)., ANR-19-CHR3-0006,UNICO,Unsupervised spiking neural networks with analog memristive devices for edge computing(2019), European Project: 773228,H2020,ERC-2017-COG,IONOS(2018) |
| المصدر: | ISSN: 1662-4548. |
| بيانات النشر: | HAL CCSD Frontiers |
| سنة النشر: | 2022 |
| مصطلحات موضوعية: | spiking neural networks, Hebbian plasticity, STDP, unsupervised learning, synaptic plasticity, modified national institute of standards and technology database (MNIST), [SPI]Engineering Sciences [physics] |
| الوصف: | International audience ; 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. |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| العلاقة: | info:eu-repo/semantics/altIdentifier/arxiv/2203.11022; info:eu-repo/grantAgreement//773228/EU/An iono-electronic neuromorphic interface for communication with living systems/IONOS; hal-03834905; https://hal.science/hal-03834905Test; https://hal.science/hal-03834905/documentTest; https://hal.science/hal-03834905/file/Garg_fnins-16-9839503.pdfTest; ARXIV: 2203.11022 |
| DOI: | 10.3389/fnins.2022.983950 |
| الإتاحة: | https://doi.org/10.3389/fnins.2022.983950Test https://hal.science/hal-03834905Test https://hal.science/hal-03834905/documentTest https://hal.science/hal-03834905/file/Garg_fnins-16-9839503.pdfTest |
| حقوق: | http://creativecommons.org/licenses/byTest/ ; info:eu-repo/semantics/OpenAccess |
| رقم الانضمام: | edsbas.F85989CE |
| قاعدة البيانات: | BASE |
| DOI: | 10.3389/fnins.2022.983950 |
|---|