FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387122304> ?p ?o ?g. }

• W4387122304 endingPage "126832" @default.
• W4387122304 startingPage "126832" @default.
• W4387122304 abstract "Spiking neural networks (SNNs) have attracted widespread attention due to their unique bio-interpretability and low-power properties, but the non-differentiability of discrete spike sequences fired by spiking neurons brings difficulties to the learning of SNNs. Recently, surrogate gradient (SG) and back-propagation through time (BPTT) have provided an excellent idea for training SNNs constructed by leaky integrate-and-fire (LIF) neuron models. The LIF neuron model has been widely used in previous SNNs due to its simplicity and low computational cost, however, this also limits its simulation of biological neuron dynamics, reducing the biological interpretability of SNNs. In this paper, we generalize SG and BPTT to SNNs constructed by spike response model (SRM) and propose the BP-SRM algorithm. Specifically, we address why BPTT succeeded in LIF neurons-based SNNs but failed in SRM neurons-based SNNs in previous researches. Then we establish an iterative form of the SRM neuron model by selecting different state variables. Based on iterable SRM, we get the spatiotemporal dependencies between the state variables of SRM neurons-based SNNs, which allows us to derive the gradient and update weights in SNN by BP-SRM. Then we design temporal channel normalization for BP-SRM and verify the performance of the SNNs on static image dataset, dynamic image dataset and engineering dataset, including Fashion-MNIST, Weather Dataset, N-MNIST, American Sign Language Dataset and bearing fault diagnosis dataset. The experiment results indicate that BP-SRM achieves the state-of-the-art performance of SNNs." @default.
• W4387122304 created "2023-09-29" @default.
• W4387122304 creator A5000345697 @default.
• W4387122304 creator A5011148961 @default.
• W4387122304 creator A5027894205 @default.
• W4387122304 creator A5042241049 @default.
• W4387122304 creator A5088503073 @default.
• W4387122304 date "2023-12-01" @default.
• W4387122304 modified "2023-10-09" @default.
• W4387122304 title "BP-SRM: A directly training algorithm for spiking neural network constructed by spike response model" @default.
• W4387122304 cites W1570411240 @default.
• W4387122304 cites W1987188408 @default.
• W4387122304 cites W1987994242 @default.
• W4387122304 cites W2062245945 @default.
• W4387122304 cites W2569813014 @default.
• W4387122304 cites W2618255684 @default.
• W4387122304 cites W2775079417 @default.
• W4387122304 cites W2779025322 @default.
• W4387122304 cites W2792432942 @default.
• W4387122304 cites W2962804204 @default.
• W4387122304 cites W2964338223 @default.
• W4387122304 cites W2974328520 @default.
• W4387122304 cites W2979879900 @default.
• W4387122304 cites W2984844508 @default.
• W4387122304 cites W2990793844 @default.
• W4387122304 cites W3006966652 @default.
• W4387122304 cites W3017751871 @default.
• W4387122304 cites W3035400263 @default.
• W4387122304 cites W3043223185 @default.
• W4387122304 cites W3065747603 @default.
• W4387122304 cites W3110802041 @default.
• W4387122304 cites W3113106473 @default.
• W4387122304 cites W3123287842 @default.
• W4387122304 cites W3127322402 @default.
• W4387122304 cites W3154963698 @default.
• W4387122304 cites W3165244476 @default.
• W4387122304 cites W3201244874 @default.
• W4387122304 cites W3203196551 @default.
• W4387122304 cites W3203274274 @default.
• W4387122304 cites W3214613446 @default.
• W4387122304 cites W4210726922 @default.
• W4387122304 cites W4223904523 @default.
• W4387122304 cites W4282968881 @default.
• W4387122304 cites W4310676090 @default.
• W4387122304 doi "https://doi.org/10.1016/j.neucom.2023.126832" @default.
• W4387122304 hasPublicationYear "2023" @default.
• W4387122304 type Work @default.
• W4387122304 citedByCount "0" @default.
• W4387122304 crossrefType "journal-article" @default.
• W4387122304 hasAuthorship W4387122304A5000345697 @default.
• W4387122304 hasAuthorship W4387122304A5011148961 @default.
• W4387122304 hasAuthorship W4387122304A5027894205 @default.
• W4387122304 hasAuthorship W4387122304A5042241049 @default.
• W4387122304 hasAuthorship W4387122304A5088503073 @default.
• W4387122304 hasConcept C11413529 @default.
• W4387122304 hasConcept C115903868 @default.
• W4387122304 hasConcept C11731999 @default.
• W4387122304 hasConcept C119857082 @default.
• W4387122304 hasConcept C136886441 @default.
• W4387122304 hasConcept C144024400 @default.
• W4387122304 hasConcept C153180895 @default.
• W4387122304 hasConcept C154945302 @default.
• W4387122304 hasConcept C190502265 @default.
• W4387122304 hasConcept C19165224 @default.
• W4387122304 hasConcept C2781067378 @default.
• W4387122304 hasConcept C2781390188 @default.
• W4387122304 hasConcept C41008148 @default.
• W4387122304 hasConcept C50644808 @default.
• W4387122304 hasConceptScore W4387122304C11413529 @default.
• W4387122304 hasConceptScore W4387122304C115903868 @default.
• W4387122304 hasConceptScore W4387122304C11731999 @default.
• W4387122304 hasConceptScore W4387122304C119857082 @default.
• W4387122304 hasConceptScore W4387122304C136886441 @default.
• W4387122304 hasConceptScore W4387122304C144024400 @default.
• W4387122304 hasConceptScore W4387122304C153180895 @default.
• W4387122304 hasConceptScore W4387122304C154945302 @default.
• W4387122304 hasConceptScore W4387122304C190502265 @default.
• W4387122304 hasConceptScore W4387122304C19165224 @default.
• W4387122304 hasConceptScore W4387122304C2781067378 @default.
• W4387122304 hasConceptScore W4387122304C2781390188 @default.
• W4387122304 hasConceptScore W4387122304C41008148 @default.
• W4387122304 hasConceptScore W4387122304C50644808 @default.
• W4387122304 hasLocation W43871223041 @default.
• W4387122304 hasOpenAccess W4387122304 @default.
• W4387122304 hasPrimaryLocation W43871223041 @default.
• W4387122304 hasRelatedWork W2542565870 @default.
• W4387122304 hasRelatedWork W2786930404 @default.
• W4387122304 hasRelatedWork W2944910788 @default.
• W4387122304 hasRelatedWork W3035000326 @default.
• W4387122304 hasRelatedWork W3102040318 @default.
• W4387122304 hasRelatedWork W3202619090 @default.
• W4387122304 hasRelatedWork W3214713078 @default.
• W4387122304 hasRelatedWork W4287724471 @default.
• W4387122304 hasRelatedWork W4321472116 @default.
• W4387122304 hasRelatedWork W4281699635 @default.
• W4387122304 hasVolume "560" @default.
• W4387122304 isParatext "false" @default.
• W4387122304 isRetracted "false" @default.

• next