Matches in SemOpenAlex for { <https://semopenalex.org/work/W4322759776> ?p ?o ?g. }
Showing items 1 to 52 of
52
with 100 items per page.
- W4322759776 abstract "Spiking Neural Networks (SNNs) are promising energy-efficient models for neuromorphic computing. For training the non-differentiable SNN models, the backpropagation through time (BPTT) with surrogate gradients (SG) method has achieved high performance. However, this method suffers from considerable memory cost and training time during training. In this paper, we propose the Spatial Learning Through Time (SLTT) method that can achieve high performance while greatly improving training efficiency compared with BPTT. First, we show that the backpropagation of SNNs through the temporal domain contributes just a little to the final calculated gradients. Thus, we propose to ignore the unimportant routes in the computational graph during backpropagation. The proposed method reduces the number of scalar multiplications and achieves a small memory occupation that is independent of the total time steps. Furthermore, we propose a variant of SLTT, called SLTT-K, that allows backpropagation only at K time steps, then the required number of scalar multiplications is further reduced and is independent of the total time steps. Experiments on both static and neuromorphic datasets demonstrate superior training efficiency and performance of our SLTT. In particular, our method achieves state-of-the-art accuracy on ImageNet, while the memory cost and training time are reduced by more than 70% and 50%, respectively, compared with BPTT." @default.
- W4322759776 created "2023-03-03" @default.
- W4322759776 creator A5004999983 @default.
- W4322759776 creator A5008007155 @default.
- W4322759776 creator A5016399094 @default.
- W4322759776 creator A5046972821 @default.
- W4322759776 creator A5053762553 @default.
- W4322759776 creator A5066792926 @default.
- W4322759776 date "2023-02-28" @default.
- W4322759776 modified "2023-10-01" @default.
- W4322759776 title "Towards Memory- and Time-Efficient Backpropagation for Training Spiking Neural Networks" @default.
- W4322759776 doi "https://doi.org/10.48550/arxiv.2302.14311" @default.
- W4322759776 hasPublicationYear "2023" @default.
- W4322759776 type Work @default.
- W4322759776 citedByCount "0" @default.
- W4322759776 crossrefType "posted-content" @default.
- W4322759776 hasAuthorship W4322759776A5004999983 @default.
- W4322759776 hasAuthorship W4322759776A5008007155 @default.
- W4322759776 hasAuthorship W4322759776A5016399094 @default.
- W4322759776 hasAuthorship W4322759776A5046972821 @default.
- W4322759776 hasAuthorship W4322759776A5053762553 @default.
- W4322759776 hasAuthorship W4322759776A5066792926 @default.
- W4322759776 hasBestOaLocation W43227597761 @default.
- W4322759776 hasConcept C119857082 @default.
- W4322759776 hasConcept C151927369 @default.
- W4322759776 hasConcept C154945302 @default.
- W4322759776 hasConcept C155032097 @default.
- W4322759776 hasConcept C41008148 @default.
- W4322759776 hasConcept C50644808 @default.
- W4322759776 hasConceptScore W4322759776C119857082 @default.
- W4322759776 hasConceptScore W4322759776C151927369 @default.
- W4322759776 hasConceptScore W4322759776C154945302 @default.
- W4322759776 hasConceptScore W4322759776C155032097 @default.
- W4322759776 hasConceptScore W4322759776C41008148 @default.
- W4322759776 hasConceptScore W4322759776C50644808 @default.
- W4322759776 hasLocation W43227597761 @default.
- W4322759776 hasLocation W43227597762 @default.
- W4322759776 hasOpenAccess W4322759776 @default.
- W4322759776 hasPrimaryLocation W43227597761 @default.
- W4322759776 hasRelatedWork W1495379181 @default.
- W4322759776 hasRelatedWork W2080531293 @default.
- W4322759776 hasRelatedWork W2157746493 @default.
- W4322759776 hasRelatedWork W2183631084 @default.
- W4322759776 hasRelatedWork W2371065793 @default.
- W4322759776 hasRelatedWork W2792697259 @default.
- W4322759776 hasRelatedWork W2894173309 @default.
- W4322759776 hasRelatedWork W2961085424 @default.
- W4322759776 hasRelatedWork W4206400463 @default.
- W4322759776 hasRelatedWork W637433680 @default.
- W4322759776 isParatext "false" @default.
- W4322759776 isRetracted "false" @default.
- W4322759776 workType "article" @default.