FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2976428661> ?p ?o ?g. }

• W2976428661 endingPage "328" @default.
• W2976428661 startingPage "319" @default.
• W2976428661 abstract "Neural networks have enabled great advances in recent times due mainly to improved parallel computing capabilities in accordance to Moore's Law, which allowed reducing the time needed for the parameter learning of complex, multi-layered neural architectures. However, with silicon technology reaching its physical limits, new types of computing paradigms are needed to increase the power efficiency of learning algorithms, especially for dealing with deep spatio-temporal knowledge on embedded applications. With the goal of mimicking the brain's power efficiency, new hardware architectures such as the SpiNNaker board have been built. Furthermore, recent works have shown that networks using spiking neurons as learning units can match classical neural networks in supervised tasks. In this paper, we show that the implementation of state-of-the-art models on both the MNIST and the event-based NMNIST digit recognition datasets is possible on neuromorphic hardware. We use two approaches, by directly converting a classical neural network to its spiking version and by training a spiking network from scratch. For both cases, software simulations and implementations into a SpiNNaker 103 machine were performed. Numerical results approaching the state of the art on digit recognition are presented, and a new method to decrease the spike rate needed for the task is proposed, which allows a significant reduction of the spikes (up to 34 times for a fully connected architecture) while preserving the accuracy of the system. With this method, we provide new insights on the capabilities offered by networks of spiking neurons to efficiently encode spatio-temporal information." @default.
• W2976428661 created "2019-10-03" @default.
• W2976428661 creator A5012539346 @default.
• W2976428661 creator A5049250191 @default.
• W2976428661 creator A5056089294 @default.
• W2976428661 creator A5079540787 @default.
• W2976428661 date "2020-01-01" @default.
• W2976428661 modified "2023-10-12" @default.
• W2976428661 title "Event-driven implementation of deep spiking convolutional neural networks for supervised classification using the SpiNNaker neuromorphic platform" @default.
• W2976428661 cites W1596035946 @default.
• W2976428661 cites W1604973310 @default.
• W2976428661 cites W1973703467 @default.
• W2976428661 cites W2002700944 @default.
• W2976428661 cites W2006872284 @default.
• W2976428661 cites W2020676607 @default.
• W2976428661 cites W2025516544 @default.
• W2976428661 cites W2064886678 @default.
• W2976428661 cites W2076063813 @default.
• W2976428661 cites W2088192327 @default.
• W2976428661 cites W2112796928 @default.
• W2976428661 cites W2159951683 @default.
• W2976428661 cites W2165639766 @default.
• W2976428661 cites W2569813014 @default.
• W2976428661 cites W2621826044 @default.
• W2976428661 cites W2775079417 @default.
• W2976428661 cites W2783525259 @default.
• W2976428661 cites W2898350988 @default.
• W2976428661 cites W2900282770 @default.
• W2976428661 cites W2919115771 @default.
• W2976428661 cites W2962804204 @default.
• W2976428661 doi "https://doi.org/10.1016/j.neunet.2019.09.008" @default.
• W2976428661 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31590013" @default.
• W2976428661 hasPublicationYear "2020" @default.
• W2976428661 type Work @default.
• W2976428661 sameAs 2976428661 @default.
• W2976428661 citedByCount "18" @default.
• W2976428661 countsByYear W29764286612020 @default.
• W2976428661 countsByYear W29764286612021 @default.
• W2976428661 countsByYear W29764286612022 @default.
• W2976428661 countsByYear W29764286612023 @default.
• W2976428661 crossrefType "journal-article" @default.
• W2976428661 hasAuthorship W2976428661A5012539346 @default.
• W2976428661 hasAuthorship W2976428661A5049250191 @default.
• W2976428661 hasAuthorship W2976428661A5056089294 @default.
• W2976428661 hasAuthorship W2976428661A5079540787 @default.
• W2976428661 hasBestOaLocation W29764286612 @default.
• W2976428661 hasConcept C108583219 @default.
• W2976428661 hasConcept C115903868 @default.
• W2976428661 hasConcept C11731999 @default.
• W2976428661 hasConcept C118524514 @default.
• W2976428661 hasConcept C119857082 @default.
• W2976428661 hasConcept C121332964 @default.
• W2976428661 hasConcept C151927369 @default.
• W2976428661 hasConcept C153180895 @default.
• W2976428661 hasConcept C154945302 @default.
• W2976428661 hasConcept C190502265 @default.
• W2976428661 hasConcept C2779662365 @default.
• W2976428661 hasConcept C2781390188 @default.
• W2976428661 hasConcept C41008148 @default.
• W2976428661 hasConcept C50644808 @default.
• W2976428661 hasConcept C62520636 @default.
• W2976428661 hasConcept C81363708 @default.
• W2976428661 hasConceptScore W2976428661C108583219 @default.
• W2976428661 hasConceptScore W2976428661C115903868 @default.
• W2976428661 hasConceptScore W2976428661C11731999 @default.
• W2976428661 hasConceptScore W2976428661C118524514 @default.
• W2976428661 hasConceptScore W2976428661C119857082 @default.
• W2976428661 hasConceptScore W2976428661C121332964 @default.
• W2976428661 hasConceptScore W2976428661C151927369 @default.
• W2976428661 hasConceptScore W2976428661C153180895 @default.
• W2976428661 hasConceptScore W2976428661C154945302 @default.
• W2976428661 hasConceptScore W2976428661C190502265 @default.
• W2976428661 hasConceptScore W2976428661C2779662365 @default.
• W2976428661 hasConceptScore W2976428661C2781390188 @default.
• W2976428661 hasConceptScore W2976428661C41008148 @default.
• W2976428661 hasConceptScore W2976428661C50644808 @default.
• W2976428661 hasConceptScore W2976428661C62520636 @default.
• W2976428661 hasConceptScore W2976428661C81363708 @default.
• W2976428661 hasFunder F4320321739 @default.
• W2976428661 hasFunder F4320332999 @default.
• W2976428661 hasFunder F4320335322 @default.
• W2976428661 hasLocation W29764286611 @default.
• W2976428661 hasLocation W29764286612 @default.
• W2976428661 hasLocation W29764286613 @default.
• W2976428661 hasLocation W29764286614 @default.
• W2976428661 hasOpenAccess W2976428661 @default.
• W2976428661 hasPrimaryLocation W29764286611 @default.
• W2976428661 hasRelatedWork W2897961390 @default.
• W2976428661 hasRelatedWork W2952496929 @default.
• W2976428661 hasRelatedWork W3159734256 @default.
• W2976428661 hasRelatedWork W3161396968 @default.
• W2976428661 hasRelatedWork W3214713078 @default.
• W2976428661 hasRelatedWork W4200377824 @default.
• W2976428661 hasRelatedWork W4281746536 @default.
• W2976428661 hasRelatedWork W4309224979 @default.
• W2976428661 hasRelatedWork W4312604567 @default.
• W2976428661 hasRelatedWork W4281699635 @default.
• W2976428661 hasVolume "121" @default.

• next