FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4304756332> ?p ?o ?g. }

• W4304756332 endingPage "044009" @default.
• W4304756332 startingPage "044009" @default.
• W4304756332 abstract "Abstract Spiking neural networks (SNNs) are largely inspired by biology and neuroscience and leverage ideas and theories to create fast and efficient learning systems. Spiking neuron models are adopted as core processing units in neuromorphic systems because they enable event-based processing. Among many neuron models, the integrate-and-fire (I&F) models are often adopted, with the simple leaky I&F (LIF) being the most used. The reason for adopting such models is their efficiency and/or biological plausibility. Nevertheless, rigorous justification for adopting LIF over other neuron models for use in artificial learning systems has not yet been studied. This work considers various neuron models in the literature and then selects computational neuron models that are single-variable, efficient, and display different types of complexities. From this selection, we make a comparative study of three simple I&F neuron models, namely the LIF, the quadratic I&F (QIF) and the exponential I&F (EIF), to understand whether the use of more complex models increases the performance of the system and whether the choice of a neuron model can be directed by the task to be completed. Neuron models are tested within an SNN trained with spike-timing dependent plasticity (STDP) on a classification task on the N-MNIST and DVS gestures datasets. Experimental results reveal that more complex neurons manifest the same ability as simpler ones to achieve high levels of accuracy on a simple dataset (N-MNIST), albeit requiring comparably more hyper-parameter tuning. However, when the data possess richer spatio-temporal features, the QIF and EIF neuron models steadily achieve better results. This suggests that accurately selecting the model based on the richness of the feature spectrum of the data could improve the whole system’s performance. Finally, the code implementing the spiking neurons in the SpykeTorch framework is made publicly available." @default.
• W4304756332 created "2022-10-13" @default.
• W4304756332 creator A5009371598 @default.
• W4304756332 creator A5013103343 @default.
• W4304756332 creator A5034018043 @default.
• W4304756332 creator A5072710973 @default.
• W4304756332 creator A5079273371 @default.
• W4304756332 date "2022-10-28" @default.
• W4304756332 modified "2023-10-10" @default.
• W4304756332 title "Simple and complex spiking neurons: perspectives and analysis in a simple STDP scenario" @default.
• W4304756332 cites W101771737 @default.
• W4304756332 cites W1549582410 @default.
• W4304756332 cites W1568617409 @default.
• W4304756332 cites W1570411240 @default.
• W4304756332 cites W1604973310 @default.
• W4304756332 cites W1666962919 @default.
• W4304756332 cites W1836848727 @default.
• W4304756332 cites W1967983190 @default.
• W4304756332 cites W1985940938 @default.
• W4304756332 cites W2007815184 @default.
• W4304756332 cites W2008284899 @default.
• W4304756332 cites W2009375605 @default.
• W4304756332 cites W2022113456 @default.
• W4304756332 cites W2025603247 @default.
• W4304756332 cites W2035383271 @default.
• W4304756332 cites W2046424015 @default.
• W4304756332 cites W2048756013 @default.
• W4304756332 cites W2056661320 @default.
• W4304756332 cites W2061191702 @default.
• W4304756332 cites W2061688414 @default.
• W4304756332 cites W2072413244 @default.
• W4304756332 cites W2096424116 @default.
• W4304756332 cites W2102916183 @default.
• W4304756332 cites W2109596721 @default.
• W4304756332 cites W2128949090 @default.
• W4304756332 cites W2129618392 @default.
• W4304756332 cites W2130360162 @default.
• W4304756332 cites W2136251560 @default.
• W4304756332 cites W2141166794 @default.
• W4304756332 cites W2157239334 @default.
• W4304756332 cites W2159951683 @default.
• W4304756332 cites W2163057446 @default.
• W4304756332 cites W2164653071 @default.
• W4304756332 cites W2252489915 @default.
• W4304756332 cites W2292222414 @default.
• W4304756332 cites W2567598763 @default.
• W4304756332 cites W2618255684 @default.
• W4304756332 cites W2737100340 @default.
• W4304756332 cites W2783525259 @default.
• W4304756332 cites W2788026236 @default.
• W4304756332 cites W2793412210 @default.
• W4304756332 cites W2793535222 @default.
• W4304756332 cites W2795655975 @default.
• W4304756332 cites W2922002199 @default.
• W4304756332 cites W2948551291 @default.
• W4304756332 cites W2950833128 @default.
• W4304756332 cites W2962804204 @default.
• W4304756332 cites W2963335874 @default.
• W4304756332 cites W2976428661 @default.
• W4304756332 cites W2979879900 @default.
• W4304756332 cites W3118707936 @default.
• W4304756332 cites W3130822715 @default.
• W4304756332 cites W3200084004 @default.
• W4304756332 cites W3205539566 @default.
• W4304756332 cites W3212354845 @default.
• W4304756332 cites W4223894936 @default.
• W4304756332 cites W4229372746 @default.
• W4304756332 cites W4297889476 @default.
• W4304756332 doi "https://doi.org/10.1088/2634-4386/ac999b" @default.
• W4304756332 hasPublicationYear "2022" @default.
• W4304756332 type Work @default.
• W4304756332 citedByCount "5" @default.
• W4304756332 countsByYear W43047563322023 @default.
• W4304756332 crossrefType "journal-article" @default.
• W4304756332 hasAuthorship W4304756332A5009371598 @default.
• W4304756332 hasAuthorship W4304756332A5013103343 @default.
• W4304756332 hasAuthorship W4304756332A5034018043 @default.
• W4304756332 hasAuthorship W4304756332A5072710973 @default.
• W4304756332 hasAuthorship W4304756332A5079273371 @default.
• W4304756332 hasBestOaLocation W43047563321 @default.
• W4304756332 hasConcept C111472728 @default.
• W4304756332 hasConcept C115903868 @default.
• W4304756332 hasConcept C11731999 @default.
• W4304756332 hasConcept C119857082 @default.
• W4304756332 hasConcept C138885662 @default.
• W4304756332 hasConcept C151927369 @default.
• W4304756332 hasConcept C15286952 @default.
• W4304756332 hasConcept C153083717 @default.
• W4304756332 hasConcept C154945302 @default.
• W4304756332 hasConcept C15744967 @default.
• W4304756332 hasConcept C169760540 @default.
• W4304756332 hasConcept C186565885 @default.
• W4304756332 hasConcept C190502265 @default.
• W4304756332 hasConcept C2778794669 @default.
• W4304756332 hasConcept C2780586882 @default.
• W4304756332 hasConcept C2781390188 @default.
• W4304756332 hasConcept C41008148 @default.
• W4304756332 hasConcept C50644808 @default.

• next