FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3202095041> ?p ?o ?g. }

• W3202095041 abstract "Spiking neural networks (SNNs) as the third generation of artificial neural networks are closer to their biological counterparts than their predecessors. SNNs have a higher computational capacity and lower power requirements than networks of sigmoidal neurons. In this paper, a new spiking neural network for pattern classification referred to as Degree of Belonging SNN (DoB-SNN) is introduced. DoB-SNN is inspired by a neuronal assembly where each neuron has a degree of belonging to every class of data being process. DoB-SNN clusters the neurons during the training process using DoBs to allocate a group of neurons to each class. A new training algorithm is presented to adjust DoBs along with the network's synaptic weights, based on Spike-Timing Dependent Plasticity (STDP) and neurons' activity for training samples. The performance of DoB-SNN is evaluated on five datasets from the UCI machine learning repository. Nested Cross-Validation is employed to determine the network's hyperparameters for each dataset and thoroughly assess generalisation capability. A detailed comparison on these datasets with three other supervised learning algorithms, including SpikeProp, SWAT, and SRESN is provided. The results show that no algorithm significantly outperforms DoB-SNN, Whereas DoB-SNN has significantly better performance than others for Liver disorders dataset (>6.10%, <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$p < 0.01$</tex> ). Accuracies obtained by DoB-SNN are significantly greater than SWAT for both Iris and Breast Cancer (>1.69%, <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$p < 0.001$</tex> ) and significantly better than SpikeProp for Iris (1.62%, <tex xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink>$p=0.04$</tex> ). In all comparisons, DoB-SNN used the smallest network, among others. DoB-SNN therefore offers significant potential as alternative SNN architecture and learning algorithm." @default.
• W3202095041 created "2021-10-11" @default.
• W3202095041 creator A5040873360 @default.
• W3202095041 creator A5042695301 @default.
• W3202095041 creator A5057339312 @default.
• W3202095041 creator A5091517700 @default.
• W3202095041 date "2021-07-18" @default.
• W3202095041 modified "2023-09-30" @default.
• W3202095041 title "DoB-SNN: A New Neuron Assembly-Inspired Spiking Neural Network for Pattern Classification" @default.
• W3202095041 cites W1203519395 @default.
• W3202095041 cites W1570411240 @default.
• W3202095041 cites W1645800954 @default.
• W3202095041 cites W2089620376 @default.
• W3202095041 cites W2162827630 @default.
• W3202095041 cites W2163982115 @default.
• W3202095041 cites W2170968634 @default.
• W3202095041 cites W2569813014 @default.
• W3202095041 cites W2618255684 @default.
• W3202095041 cites W2735894830 @default.
• W3202095041 cites W2736237086 @default.
• W3202095041 cites W2779025322 @default.
• W3202095041 cites W2798878556 @default.
• W3202095041 cites W2805087868 @default.
• W3202095041 cites W2908664843 @default.
• W3202095041 cites W2942803402 @default.
• W3202095041 cites W3033478716 @default.
• W3202095041 cites W3045777102 @default.
• W3202095041 cites W3105516366 @default.
• W3202095041 cites W4231081240 @default.
• W3202095041 doi "https://doi.org/10.1109/ijcnn52387.2021.9534283" @default.
• W3202095041 hasPublicationYear "2021" @default.
• W3202095041 type Work @default.
• W3202095041 sameAs 3202095041 @default.
• W3202095041 citedByCount "2" @default.
• W3202095041 countsByYear W32020950412022 @default.
• W3202095041 countsByYear W32020950412023 @default.
• W3202095041 crossrefType "proceedings-article" @default.
• W3202095041 hasAuthorship W3202095041A5040873360 @default.
• W3202095041 hasAuthorship W3202095041A5042695301 @default.
• W3202095041 hasAuthorship W3202095041A5057339312 @default.
• W3202095041 hasAuthorship W3202095041A5091517700 @default.
• W3202095041 hasConcept C111919701 @default.
• W3202095041 hasConcept C11731999 @default.
• W3202095041 hasConcept C119857082 @default.
• W3202095041 hasConcept C153180895 @default.
• W3202095041 hasConcept C154945302 @default.
• W3202095041 hasConcept C2777212361 @default.
• W3202095041 hasConcept C41008148 @default.
• W3202095041 hasConcept C50644808 @default.
• W3202095041 hasConcept C98045186 @default.
• W3202095041 hasConceptScore W3202095041C111919701 @default.
• W3202095041 hasConceptScore W3202095041C11731999 @default.
• W3202095041 hasConceptScore W3202095041C119857082 @default.
• W3202095041 hasConceptScore W3202095041C153180895 @default.
• W3202095041 hasConceptScore W3202095041C154945302 @default.
• W3202095041 hasConceptScore W3202095041C2777212361 @default.
• W3202095041 hasConceptScore W3202095041C41008148 @default.
• W3202095041 hasConceptScore W3202095041C50644808 @default.
• W3202095041 hasConceptScore W3202095041C98045186 @default.
• W3202095041 hasFunder F4320334627 @default.
• W3202095041 hasLocation W32020950411 @default.
• W3202095041 hasOpenAccess W3202095041 @default.
• W3202095041 hasPrimaryLocation W32020950411 @default.
• W3202095041 hasRelatedWork W2386387936 @default.
• W3202095041 hasRelatedWork W2961085424 @default.
• W3202095041 hasRelatedWork W3046775127 @default.
• W3202095041 hasRelatedWork W3170094116 @default.
• W3202095041 hasRelatedWork W4205958290 @default.
• W3202095041 hasRelatedWork W4285260836 @default.
• W3202095041 hasRelatedWork W4286629047 @default.
• W3202095041 hasRelatedWork W4306321456 @default.
• W3202095041 hasRelatedWork W4306674287 @default.
• W3202095041 hasRelatedWork W4224009465 @default.
• W3202095041 isParatext "false" @default.
• W3202095041 isRetracted "false" @default.
• W3202095041 magId "3202095041" @default.
• W3202095041 workType "article" @default.