Matches in SemOpenAlex for { <https://semopenalex.org/work/W3212044614> ?p ?o ?g. }
Showing items 1 to 80 of
80
with 100 items per page.
- W3212044614 abstract "Spiking Neural Networks (SNNs) are being explored for their potential energy efficiency benefits due to sparse, event-driven computation. Non-spiking artificial neural networks are typically trained with stochastic gradient descent using backpropagation. The calculation of true gradients for backpropagation in spiking neural networks is impeded by the non-differentiable firing events of spiking neurons. On the other hand, using approximate gradients is effective, but computationally expensive over many time steps. One common technique, then, for training a spiking neural network is to train a topologically-equivalent non-spiking network, and then convert it to an spiking network, replacing real-valued inputs with proportionally rate-encoded Poisson spike trains. Converted SNNs function sufficiently well because the mean pre-firing membrane potential of a spiking neuron is proportional to the dot product of the input rate vector and the neuron weight vector, similar to the functionality of a non-spiking network. However, this conversion only considers the mean and not the temporal variance of the membrane potential. As the standard deviation of the pre-firing membrane potential is proportional to the L4-norm of the neuron weight vector, we propose a weight adjustment based on the L4-norm during the conversion process in order to improve classification accuracy of the converted network." @default.
- W3212044614 created "2021-11-22" @default.
- W3212044614 creator A5031161187 @default.
- W3212044614 creator A5087698063 @default.
- W3212044614 date "2021-11-17" @default.
- W3212044614 modified "2023-09-27" @default.
- W3212044614 title "L4-Norm Weight Adjustments for Converted Spiking Neural Networks" @default.
- W3212044614 cites W1645800954 @default.
- W3212044614 cites W2055282041 @default.
- W3212044614 cites W2964338223 @default.
- W3212044614 cites W2995289984 @default.
- W3212044614 cites W3003366625 @default.
- W3212044614 hasPublicationYear "2021" @default.
- W3212044614 type Work @default.
- W3212044614 sameAs 3212044614 @default.
- W3212044614 citedByCount "0" @default.
- W3212044614 crossrefType "posted-content" @default.
- W3212044614 hasAuthorship W3212044614A5031161187 @default.
- W3212044614 hasAuthorship W3212044614A5087698063 @default.
- W3212044614 hasConcept C11413529 @default.
- W3212044614 hasConcept C115903868 @default.
- W3212044614 hasConcept C11731999 @default.
- W3212044614 hasConcept C153180895 @default.
- W3212044614 hasConcept C153258448 @default.
- W3212044614 hasConcept C154945302 @default.
- W3212044614 hasConcept C155032097 @default.
- W3212044614 hasConcept C17744445 @default.
- W3212044614 hasConcept C191795146 @default.
- W3212044614 hasConcept C199539241 @default.
- W3212044614 hasConcept C2781390188 @default.
- W3212044614 hasConcept C2909946758 @default.
- W3212044614 hasConcept C33010914 @default.
- W3212044614 hasConcept C38365724 @default.
- W3212044614 hasConcept C41008148 @default.
- W3212044614 hasConcept C50644808 @default.
- W3212044614 hasConcept C66949984 @default.
- W3212044614 hasConceptScore W3212044614C11413529 @default.
- W3212044614 hasConceptScore W3212044614C115903868 @default.
- W3212044614 hasConceptScore W3212044614C11731999 @default.
- W3212044614 hasConceptScore W3212044614C153180895 @default.
- W3212044614 hasConceptScore W3212044614C153258448 @default.
- W3212044614 hasConceptScore W3212044614C154945302 @default.
- W3212044614 hasConceptScore W3212044614C155032097 @default.
- W3212044614 hasConceptScore W3212044614C17744445 @default.
- W3212044614 hasConceptScore W3212044614C191795146 @default.
- W3212044614 hasConceptScore W3212044614C199539241 @default.
- W3212044614 hasConceptScore W3212044614C2781390188 @default.
- W3212044614 hasConceptScore W3212044614C2909946758 @default.
- W3212044614 hasConceptScore W3212044614C33010914 @default.
- W3212044614 hasConceptScore W3212044614C38365724 @default.
- W3212044614 hasConceptScore W3212044614C41008148 @default.
- W3212044614 hasConceptScore W3212044614C50644808 @default.
- W3212044614 hasConceptScore W3212044614C66949984 @default.
- W3212044614 hasLocation W32120446141 @default.
- W3212044614 hasOpenAccess W3212044614 @default.
- W3212044614 hasPrimaryLocation W32120446141 @default.
- W3212044614 hasRelatedWork W140103524 @default.
- W3212044614 hasRelatedWork W1941491374 @default.
- W3212044614 hasRelatedWork W2003172116 @default.
- W3212044614 hasRelatedWork W2004168727 @default.
- W3212044614 hasRelatedWork W2028553085 @default.
- W3212044614 hasRelatedWork W2120884455 @default.
- W3212044614 hasRelatedWork W2626540870 @default.
- W3212044614 hasRelatedWork W2766422095 @default.
- W3212044614 hasRelatedWork W2787186454 @default.
- W3212044614 hasRelatedWork W2908861709 @default.
- W3212044614 hasRelatedWork W3025338791 @default.
- W3212044614 hasRelatedWork W3084655686 @default.
- W3212044614 hasRelatedWork W3100354136 @default.
- W3212044614 hasRelatedWork W3149826313 @default.
- W3212044614 hasRelatedWork W3166154962 @default.
- W3212044614 hasRelatedWork W3199022968 @default.
- W3212044614 hasRelatedWork W91754411 @default.
- W3212044614 hasRelatedWork W968148860 @default.
- W3212044614 hasRelatedWork W3071407064 @default.
- W3212044614 hasRelatedWork W3153937403 @default.
- W3212044614 isParatext "false" @default.
- W3212044614 isRetracted "false" @default.
- W3212044614 magId "3212044614" @default.
- W3212044614 workType "article" @default.