Matches in SemOpenAlex for { <https://semopenalex.org/work/W4288049765> ?p ?o ?g. }
Showing items 1 to 72 of
72
with 100 items per page.
- W4288049765 abstract "Spiking Neural Networks (SNNs) have been attached great importance due to the distinctive properties of low power consumption, biological plausibility, and adversarial robustness. The most effective way to train deep SNNs is through ANN-to-SNN conversion, which have yielded the best performance in deep network structure and large-scale datasets. However, there is a trade-off between accuracy and latency. In order to achieve high precision as original ANNs, a long simulation time is needed to match the firing rate of a spiking neuron with the activation value of an analog neuron, which impedes the practical application of SNN. In this paper, we aim to achieve high-performance converted SNNs with extremely low latency (fewer than 32 time-steps). We start by theoretically analyzing ANN-to-SNN conversion and show that scaling the thresholds does play a similar role as weight normalization. Instead of introducing constraints that facilitate ANN-to-SNN conversion at the cost of model capacity, we applied a more direct way by optimizing the initial membrane potential to reduce the conversion loss in each layer. Besides, we demonstrate that optimal initialization of membrane potentials can implement expected error-free ANN-to-SNN conversion. We evaluate our algorithm on the CIFAR-10, CIFAR-100 and ImageNet datasets and achieve state-of-the-art accuracy, using fewer time-steps. For example, we reach top-1 accuracy of 93.38% on CIFAR-10 with 16 time-steps. Moreover, our method can be applied to other ANN-SNN conversion methodologies and remarkably promote performance when the time-steps is small." @default.
- W4288049765 created "2022-07-27" @default.
- W4288049765 creator A5030879654 @default.
- W4288049765 creator A5048087489 @default.
- W4288049765 creator A5058066577 @default.
- W4288049765 creator A5087154321 @default.
- W4288049765 date "2022-02-03" @default.
- W4288049765 modified "2023-09-26" @default.
- W4288049765 title "Optimized Potential Initialization for Low-latency Spiking Neural Networks" @default.
- W4288049765 doi "https://doi.org/10.48550/arxiv.2202.01440" @default.
- W4288049765 hasPublicationYear "2022" @default.
- W4288049765 type Work @default.
- W4288049765 citedByCount "1" @default.
- W4288049765 countsByYear W42880497652023 @default.
- W4288049765 crossrefType "posted-content" @default.
- W4288049765 hasAuthorship W4288049765A5030879654 @default.
- W4288049765 hasAuthorship W4288049765A5048087489 @default.
- W4288049765 hasAuthorship W4288049765A5058066577 @default.
- W4288049765 hasAuthorship W4288049765A5087154321 @default.
- W4288049765 hasBestOaLocation W42880497651 @default.
- W4288049765 hasConcept C104317684 @default.
- W4288049765 hasConcept C114466953 @default.
- W4288049765 hasConcept C11731999 @default.
- W4288049765 hasConcept C136886441 @default.
- W4288049765 hasConcept C144024400 @default.
- W4288049765 hasConcept C154945302 @default.
- W4288049765 hasConcept C185592680 @default.
- W4288049765 hasConcept C19165224 @default.
- W4288049765 hasConcept C199360897 @default.
- W4288049765 hasConcept C2984842247 @default.
- W4288049765 hasConcept C41008148 @default.
- W4288049765 hasConcept C46686674 @default.
- W4288049765 hasConcept C50644808 @default.
- W4288049765 hasConcept C55493867 @default.
- W4288049765 hasConcept C63479239 @default.
- W4288049765 hasConcept C76155785 @default.
- W4288049765 hasConcept C82876162 @default.
- W4288049765 hasConcept C97385483 @default.
- W4288049765 hasConceptScore W4288049765C104317684 @default.
- W4288049765 hasConceptScore W4288049765C114466953 @default.
- W4288049765 hasConceptScore W4288049765C11731999 @default.
- W4288049765 hasConceptScore W4288049765C136886441 @default.
- W4288049765 hasConceptScore W4288049765C144024400 @default.
- W4288049765 hasConceptScore W4288049765C154945302 @default.
- W4288049765 hasConceptScore W4288049765C185592680 @default.
- W4288049765 hasConceptScore W4288049765C19165224 @default.
- W4288049765 hasConceptScore W4288049765C199360897 @default.
- W4288049765 hasConceptScore W4288049765C2984842247 @default.
- W4288049765 hasConceptScore W4288049765C41008148 @default.
- W4288049765 hasConceptScore W4288049765C46686674 @default.
- W4288049765 hasConceptScore W4288049765C50644808 @default.
- W4288049765 hasConceptScore W4288049765C55493867 @default.
- W4288049765 hasConceptScore W4288049765C63479239 @default.
- W4288049765 hasConceptScore W4288049765C76155785 @default.
- W4288049765 hasConceptScore W4288049765C82876162 @default.
- W4288049765 hasConceptScore W4288049765C97385483 @default.
- W4288049765 hasLocation W42880497651 @default.
- W4288049765 hasOpenAccess W4288049765 @default.
- W4288049765 hasPrimaryLocation W42880497651 @default.
- W4288049765 hasRelatedWork W1836465849 @default.
- W4288049765 hasRelatedWork W2240647871 @default.
- W4288049765 hasRelatedWork W2887550073 @default.
- W4288049765 hasRelatedWork W2977257638 @default.
- W4288049765 hasRelatedWork W3180497743 @default.
- W4288049765 hasRelatedWork W4221157818 @default.
- W4288049765 hasRelatedWork W4288049765 @default.
- W4288049765 hasRelatedWork W4288095186 @default.
- W4288049765 hasRelatedWork W4288621368 @default.
- W4288049765 hasRelatedWork W4309452521 @default.
- W4288049765 isParatext "false" @default.
- W4288049765 isRetracted "false" @default.
- W4288049765 workType "article" @default.