Matches in SemOpenAlex for { <https://semopenalex.org/work/W4308575307> ?p ?o ?g. }
- W4308575307 abstract "Spiking Neural Networks (SNNs) can drastically improve the energy efficiency of neuromorphic computing through network sparsity and event-driven execution. Thus, SNNs have the potential to support practical cognitive tasks on resource constrained platforms, such as edge devices. To realize this, SNN requires energy-efficient hardware which can run applications with a limited energy budget. However, the conventional CMOS implementations cannot achieve this goal due to the various architectural and technological challenges. In this work, we address these issues by developing an energy-efficient and accurate SNN hardware based on Computation In-Memory (CIM) architecture using Resistive Random Access Memory (RRAM) devices. The developed SNN architecture is based on unsupervised Spike Time Dependent Plasticity (STDP) learning algorithm with online learning capability. Simulation results show that the proposed architecture is energy-efficient with a consumption of ≈20 fJ per spike, while maintaining state-of-the-art inference accuracy of 95% when evaluated using the MNIST dataset." @default.
- W4308575307 created "2022-11-12" @default.
- W4308575307 creator A5005739146 @default.
- W4308575307 creator A5017450486 @default.
- W4308575307 creator A5025407017 @default.
- W4308575307 creator A5028499515 @default.
- W4308575307 date "2022-10-03" @default.
- W4308575307 modified "2023-10-16" @default.
- W4308575307 title "Energy-Efficient SNN Implementation Using RRAM-Based Computation In-Memory (CIM)" @default.
- W4308575307 cites W1486852018 @default.
- W4308575307 cites W1514853588 @default.
- W4308575307 cites W1530842230 @default.
- W4308575307 cites W1570411240 @default.
- W4308575307 cites W1976075132 @default.
- W4308575307 cites W1985940938 @default.
- W4308575307 cites W2001465022 @default.
- W4308575307 cites W2004085402 @default.
- W4308575307 cites W2024894333 @default.
- W4308575307 cites W2038511109 @default.
- W4308575307 cites W2098881438 @default.
- W4308575307 cites W2128378732 @default.
- W4308575307 cites W2138913040 @default.
- W4308575307 cites W2160361560 @default.
- W4308575307 cites W2433248078 @default.
- W4308575307 cites W2513853720 @default.
- W4308575307 cites W2771687934 @default.
- W4308575307 cites W2782791387 @default.
- W4308575307 cites W2783053830 @default.
- W4308575307 cites W2800613970 @default.
- W4308575307 cites W2808550672 @default.
- W4308575307 cites W2809171749 @default.
- W4308575307 cites W2818007000 @default.
- W4308575307 cites W2905533880 @default.
- W4308575307 cites W2916724483 @default.
- W4308575307 cites W2920081941 @default.
- W4308575307 cites W2926419149 @default.
- W4308575307 cites W2962953132 @default.
- W4308575307 cites W2963743287 @default.
- W4308575307 cites W2970793768 @default.
- W4308575307 cites W2979879900 @default.
- W4308575307 cites W3006299183 @default.
- W4308575307 cites W3009643182 @default.
- W4308575307 cites W3032942119 @default.
- W4308575307 cites W3103266921 @default.
- W4308575307 cites W3131336557 @default.
- W4308575307 cites W3155456425 @default.
- W4308575307 cites W3176428941 @default.
- W4308575307 cites W3200309693 @default.
- W4308575307 cites W4225377446 @default.
- W4308575307 cites W4231081240 @default.
- W4308575307 cites W4232753305 @default.
- W4308575307 cites W4238614602 @default.
- W4308575307 cites W4251155475 @default.
- W4308575307 doi "https://doi.org/10.1109/vlsi-soc54400.2022.9939654" @default.
- W4308575307 hasPublicationYear "2022" @default.
- W4308575307 type Work @default.
- W4308575307 citedByCount "2" @default.
- W4308575307 countsByYear W43085753072023 @default.
- W4308575307 crossrefType "proceedings-article" @default.
- W4308575307 hasAuthorship W4308575307A5005739146 @default.
- W4308575307 hasAuthorship W4308575307A5017450486 @default.
- W4308575307 hasAuthorship W4308575307A5025407017 @default.
- W4308575307 hasAuthorship W4308575307A5028499515 @default.
- W4308575307 hasConcept C105795698 @default.
- W4308575307 hasConcept C113775141 @default.
- W4308575307 hasConcept C11413529 @default.
- W4308575307 hasConcept C11731999 @default.
- W4308575307 hasConcept C118524514 @default.
- W4308575307 hasConcept C119599485 @default.
- W4308575307 hasConcept C121332964 @default.
- W4308575307 hasConcept C127413603 @default.
- W4308575307 hasConcept C149635348 @default.
- W4308575307 hasConcept C151927369 @default.
- W4308575307 hasConcept C154945302 @default.
- W4308575307 hasConcept C165801399 @default.
- W4308575307 hasConcept C173608175 @default.
- W4308575307 hasConcept C182019814 @default.
- W4308575307 hasConcept C186370098 @default.
- W4308575307 hasConcept C18903297 @default.
- W4308575307 hasConcept C190502265 @default.
- W4308575307 hasConcept C2742236 @default.
- W4308575307 hasConcept C2776214188 @default.
- W4308575307 hasConcept C2780165032 @default.
- W4308575307 hasConcept C33923547 @default.
- W4308575307 hasConcept C41008148 @default.
- W4308575307 hasConcept C45374587 @default.
- W4308575307 hasConcept C50644808 @default.
- W4308575307 hasConcept C62520636 @default.
- W4308575307 hasConcept C86803240 @default.
- W4308575307 hasConceptScore W4308575307C105795698 @default.
- W4308575307 hasConceptScore W4308575307C113775141 @default.
- W4308575307 hasConceptScore W4308575307C11413529 @default.
- W4308575307 hasConceptScore W4308575307C11731999 @default.
- W4308575307 hasConceptScore W4308575307C118524514 @default.
- W4308575307 hasConceptScore W4308575307C119599485 @default.
- W4308575307 hasConceptScore W4308575307C121332964 @default.
- W4308575307 hasConceptScore W4308575307C127413603 @default.
- W4308575307 hasConceptScore W4308575307C149635348 @default.
- W4308575307 hasConceptScore W4308575307C151927369 @default.
- W4308575307 hasConceptScore W4308575307C154945302 @default.