SPICE-Level Demonstration of Unsupervised Learning With Spintronic Synapses in Spiking Neural Networks
Spiking Neural Networks (SNNs) are Artificial Neural Networks which promise to mimic the biological brain processing with unsupervised online learning capability for various cognitive tasks. However, SNN hardware implementation with online learning support is not trivial and might prove highly ineff...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10551821/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592939669258240 |
|---|---|
| author | Salah Daddinounou Anteneh Gebregiorgis Said Hamdioui Elena-Ioana Vatajelu |
| author_facet | Salah Daddinounou Anteneh Gebregiorgis Said Hamdioui Elena-Ioana Vatajelu |
| author_sort | Salah Daddinounou |
| collection | DOAJ |
| description | Spiking Neural Networks (SNNs) are Artificial Neural Networks which promise to mimic the biological brain processing with unsupervised online learning capability for various cognitive tasks. However, SNN hardware implementation with online learning support is not trivial and might prove highly inefficient. This paper proposes an energy-efficient hardware implementation for SNN synapses. The implementation is based on parallel-connected Magnetic Tunnel Junction (MTJ) devices and exploits their inherent stochasticity. In addition, it uses a dedicated unsupervised learning rule based on optimized Spike-Timing-Dependent Plasticity (STDP). To facilitate the design of the SNN, its training and evaluation, an open-source Python-based platform is developed; it takes as input the SNN parameters and discrete circuit components, and it automatically generates the associated full netlist in SPICE then launches the simulation; moreover, it extracts the simulation results and makes them available in python for evaluation and manipulation. Unlike conventional neuromorphic hardware that relies on simple weight mapping post-off-line training, our approach emphasizes continuous, unsupervised learning, ensuring an energy efficiency of 11.2nW per synaptic update during training and as low as 109fJ/spike during inference. |
| format | Article |
| id | doaj-art-8e6cc837f35e46e0af586bb439624a8d |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-8e6cc837f35e46e0af586bb439624a8d2025-01-21T00:01:22ZengIEEEIEEE Access2169-35362025-01-01136845685410.1109/ACCESS.2024.341151910551821SPICE-Level Demonstration of Unsupervised Learning With Spintronic Synapses in Spiking Neural NetworksSalah Daddinounou0Anteneh Gebregiorgis1https://orcid.org/0000-0002-8408-5691Said Hamdioui2https://orcid.org/0000-0002-8961-0387Elena-Ioana Vatajelu3https://orcid.org/0000-0002-4588-1812Univ. Grenoble Alpes, CNRS, Grenoble INP, TIMA, Grenoble, FranceDepartment of Quantum and Computer Engineering, Delft University of Technology, Delft, CD, The NetherlandsDepartment of Quantum and Computer Engineering, Delft University of Technology, Delft, CD, The NetherlandsUniv. Grenoble Alpes, CNRS, Grenoble INP, TIMA, Grenoble, FranceSpiking Neural Networks (SNNs) are Artificial Neural Networks which promise to mimic the biological brain processing with unsupervised online learning capability for various cognitive tasks. However, SNN hardware implementation with online learning support is not trivial and might prove highly inefficient. This paper proposes an energy-efficient hardware implementation for SNN synapses. The implementation is based on parallel-connected Magnetic Tunnel Junction (MTJ) devices and exploits their inherent stochasticity. In addition, it uses a dedicated unsupervised learning rule based on optimized Spike-Timing-Dependent Plasticity (STDP). To facilitate the design of the SNN, its training and evaluation, an open-source Python-based platform is developed; it takes as input the SNN parameters and discrete circuit components, and it automatically generates the associated full netlist in SPICE then launches the simulation; moreover, it extracts the simulation results and makes them available in python for evaluation and manipulation. Unlike conventional neuromorphic hardware that relies on simple weight mapping post-off-line training, our approach emphasizes continuous, unsupervised learning, ensuring an energy efficiency of 11.2nW per synaptic update during training and as low as 109fJ/spike during inference.https://ieeexplore.ieee.org/document/10551821/MTJneuromorphicSNNSTDPunsupervised learning |
| spellingShingle | Salah Daddinounou Anteneh Gebregiorgis Said Hamdioui Elena-Ioana Vatajelu SPICE-Level Demonstration of Unsupervised Learning With Spintronic Synapses in Spiking Neural Networks IEEE Access MTJ neuromorphic SNN STDP unsupervised learning |
| title | SPICE-Level Demonstration of Unsupervised Learning With Spintronic Synapses in Spiking Neural Networks |
| title_full | SPICE-Level Demonstration of Unsupervised Learning With Spintronic Synapses in Spiking Neural Networks |
| title_fullStr | SPICE-Level Demonstration of Unsupervised Learning With Spintronic Synapses in Spiking Neural Networks |
| title_full_unstemmed | SPICE-Level Demonstration of Unsupervised Learning With Spintronic Synapses in Spiking Neural Networks |
| title_short | SPICE-Level Demonstration of Unsupervised Learning With Spintronic Synapses in Spiking Neural Networks |
| title_sort | spice level demonstration of unsupervised learning with spintronic synapses in spiking neural networks |
| topic | MTJ neuromorphic SNN STDP unsupervised learning |
| url | https://ieeexplore.ieee.org/document/10551821/ |
| work_keys_str_mv | AT salahdaddinounou spiceleveldemonstrationofunsupervisedlearningwithspintronicsynapsesinspikingneuralnetworks AT antenehgebregiorgis spiceleveldemonstrationofunsupervisedlearningwithspintronicsynapsesinspikingneuralnetworks AT saidhamdioui spiceleveldemonstrationofunsupervisedlearningwithspintronicsynapsesinspikingneuralnetworks AT elenaioanavatajelu spiceleveldemonstrationofunsupervisedlearningwithspintronicsynapsesinspikingneuralnetworks |