FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3083893447> ?p ?o ?g. }

• W3083893447 endingPage "58" @default.
• W3083893447 startingPage "47" @default.
• W3083893447 abstract "It is now known that the spiking neuron is a basic unit of spiking neural networks (SNNs). Spiking neurons modulate the nervous cells via receiving external incentives, generation of action potential and firing spikes. The SNNs usually used for pattern recognition tasks or complex computation depending on the brain-like characteristic. Although the SNNs have no advantages comparing with the deep neural networks in terms of classification accuracy, the SNNs have more characteristics of biological neurons. In this paper, a hierarchical SNN, comprising convolutional and pooling layers, is designed. The proposed SNN consists of excitatory and inhibitory neurons based on the mechanism of the primate brain. A temporal coding (rank order) manner is used to encode the input patterns. It depends on the rank of the spike arrival on post synapses to establish the priority of input spikes for a particular pattern. The spike-timing-dependent plasticity (STDP) learning rule is used in convolutional layers to extract visual features in an unsupervised learning manner. During the classification stage, a lateral inhibition mechanism is used to prevent the non-firing neurons and produce distinguishable results. In order to improve the performance of our SNN, an ensemble SNN architecture using the voting method is proposed, and transfer learning is used to avoid re-training the SNN when solving the different tasks. The hand-written digits classification task on MNIST, CIFAR-10, and BreaKHis databases are used to verify the performance of the proposed SNN. Experimental results show that by using the ensemble architecture and transfer learning, the classification accuracy of 99.27% for the MNIST database, overall accuracy is 93% for the CIFAR-10 database, and overall accuracy is 96.97% for BreaKHis database. In the meantime, this work achieves a better performance than the benchmarking approaches. Taken together, the results of our work suggest that the ensemble SNN architecture with transfer learning is key to improving the performance of the SNN." @default.
• W3083893447 created "2020-09-14" @default.
• W3083893447 creator A5041173904 @default.
• W3083893447 creator A5072710254 @default.
• W3083893447 date "2021-01-01" @default.
• W3083893447 modified "2023-10-02" @default.
• W3083893447 title "An ensemble unsupervised spiking neural network for objective recognition" @default.
• W3083893447 cites W1645800954 @default.
• W3083893447 cites W2000266578 @default.
• W3083893447 cites W2020676607 @default.
• W3083893447 cites W2025166739 @default.
• W3083893447 cites W2076063813 @default.
• W3083893447 cites W2096671349 @default.
• W3083893447 cites W2112796928 @default.
• W3083893447 cites W2155377787 @default.
• W3083893447 cites W2162827630 @default.
• W3083893447 cites W2163740524 @default.
• W3083893447 cites W2165396124 @default.
• W3083893447 cites W2260550436 @default.
• W3083893447 cites W2314470091 @default.
• W3083893447 cites W2344480160 @default.
• W3083893447 cites W2522002261 @default.
• W3083893447 cites W2532724900 @default.
• W3083893447 cites W2554892747 @default.
• W3083893447 cites W2775079417 @default.
• W3083893447 cites W2779025322 @default.
• W3083893447 cites W2787907153 @default.
• W3083893447 cites W2798878556 @default.
• W3083893447 cites W2805852360 @default.
• W3083893447 cites W2808518417 @default.
• W3083893447 cites W2902264310 @default.
• W3083893447 cites W2911725274 @default.
• W3083893447 cites W2913994460 @default.
• W3083893447 cites W2917262027 @default.
• W3083893447 cites W2924232824 @default.
• W3083893447 cites W2939470209 @default.
• W3083893447 cites W2940297489 @default.
• W3083893447 cites W2943455019 @default.
• W3083893447 cites W2945377681 @default.
• W3083893447 cites W2962899068 @default.
• W3083893447 cites W2977501091 @default.
• W3083893447 cites W2984687858 @default.
• W3083893447 doi "https://doi.org/10.1016/j.neucom.2020.07.109" @default.
• W3083893447 hasPublicationYear "2021" @default.
• W3083893447 type Work @default.
• W3083893447 sameAs 3083893447 @default.
• W3083893447 citedByCount "16" @default.
• W3083893447 countsByYear W30838934472021 @default.
• W3083893447 countsByYear W30838934472022 @default.
• W3083893447 countsByYear W30838934472023 @default.
• W3083893447 crossrefType "journal-article" @default.
• W3083893447 hasAuthorship W3083893447A5041173904 @default.
• W3083893447 hasAuthorship W3083893447A5072710254 @default.
• W3083893447 hasConcept C11731999 @default.
• W3083893447 hasConcept C119857082 @default.
• W3083893447 hasConcept C153180895 @default.
• W3083893447 hasConcept C154945302 @default.
• W3083893447 hasConcept C159919123 @default.
• W3083893447 hasConcept C170493617 @default.
• W3083893447 hasConcept C185592680 @default.
• W3083893447 hasConcept C190502265 @default.
• W3083893447 hasConcept C25274449 @default.
• W3083893447 hasConcept C41008148 @default.
• W3083893447 hasConcept C50644808 @default.
• W3083893447 hasConcept C55493867 @default.
• W3083893447 hasConcept C70437156 @default.
• W3083893447 hasConcept C77637269 @default.
• W3083893447 hasConcept C81363708 @default.
• W3083893447 hasConceptScore W3083893447C11731999 @default.
• W3083893447 hasConceptScore W3083893447C119857082 @default.
• W3083893447 hasConceptScore W3083893447C153180895 @default.
• W3083893447 hasConceptScore W3083893447C154945302 @default.
• W3083893447 hasConceptScore W3083893447C159919123 @default.
• W3083893447 hasConceptScore W3083893447C170493617 @default.
• W3083893447 hasConceptScore W3083893447C185592680 @default.
• W3083893447 hasConceptScore W3083893447C190502265 @default.
• W3083893447 hasConceptScore W3083893447C25274449 @default.
• W3083893447 hasConceptScore W3083893447C41008148 @default.
• W3083893447 hasConceptScore W3083893447C50644808 @default.
• W3083893447 hasConceptScore W3083893447C55493867 @default.
• W3083893447 hasConceptScore W3083893447C70437156 @default.
• W3083893447 hasConceptScore W3083893447C77637269 @default.
• W3083893447 hasConceptScore W3083893447C81363708 @default.
• W3083893447 hasFunder F4320321001 @default.
• W3083893447 hasLocation W30838934471 @default.
• W3083893447 hasOpenAccess W3083893447 @default.
• W3083893447 hasPrimaryLocation W30838934471 @default.
• W3083893447 hasRelatedWork W2556793986 @default.
• W3083893447 hasRelatedWork W2792873414 @default.
• W3083893447 hasRelatedWork W2914384215 @default.
• W3083893447 hasRelatedWork W2944910788 @default.
• W3083893447 hasRelatedWork W2952868231 @default.
• W3083893447 hasRelatedWork W2976775487 @default.
• W3083893447 hasRelatedWork W3167950509 @default.
• W3083893447 hasRelatedWork W3202619090 @default.
• W3083893447 hasRelatedWork W4312604567 @default.
• W3083893447 hasRelatedWork W4312764229 @default.
• W3083893447 hasVolume "419" @default.

• next