FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3042512022> ?p ?o ?g. }

• W3042512022 abstract "Spiking Neural Networks (SNNs) are gaining interest due to their event-driven processing which potentially consumes low power/energy computations in hardware platforms, while offering unsupervised learning capability due to the spike-timing-dependent plasticity (STDP) rule. However, state-of-the-art SNNs require a large memory footprint to achieve high accuracy, thereby making them difficult to be deployed on embedded systems, for instance on battery-powered mobile devices and IoT Edge nodes. Towards this, we propose FSpiNN, an optimization framework for obtaining memory- and energy-efficient SNNs for training and inference processing, with unsupervised learning capability while maintaining accuracy. It is achieved by (1) reducing the computational requirements of neuronal and STDP operations, (2) improving the accuracy of STDP-based learning, (3) compressing the SNN through a fixed-point quantization, and (4) incorporating the memory and energy requirements in the optimization process. FSpiNN reduces the computational requirements by reducing the number of neuronal operations, the STDP-based synaptic weight updates, and the STDP complexity. To improve the accuracy of learning, FSpiNN employs timestep-based synaptic weight updates, and adaptively determines the STDP potentiation factor and the effective inhibition strength. The experimental results show that, as compared to the state-of-the-art work, FSpiNN achieves 7.5x memory saving, and improves the energy-efficiency by 3.5x on average for training and by 1.8x on average for inference, across MNIST and Fashion MNIST datasets, with no accuracy loss for a network with 4900 excitatory neurons, thereby enabling energy-efficient SNNs for edge devices/embedded systems." @default.
• W3042512022 created "2020-07-23" @default.
• W3042512022 creator A5030422145 @default.
• W3042512022 creator A5057618925 @default.
• W3042512022 date "2020-07-17" @default.
• W3042512022 modified "2023-09-27" @default.
• W3042512022 title "FSpiNN: An Optimization Framework for Memory- and Energy-Efficient Spiking Neural Networks." @default.
• W3042512022 cites W1570411240 @default.
• W3042512022 cites W1604973310 @default.
• W3042512022 cites W1976433270 @default.
• W3042512022 cites W1999085092 @default.
• W3042512022 cites W2038511109 @default.
• W3042512022 cites W2096671349 @default.
• W3042512022 cites W2112796928 @default.
• W3042512022 cites W2133925073 @default.
• W3042512022 cites W2147101007 @default.
• W3042512022 cites W2157239334 @default.
• W3042512022 cites W2162003043 @default.
• W3042512022 cites W2237922334 @default.
• W3042512022 cites W2605366333 @default.
• W3042512022 cites W2612662066 @default.
• W3042512022 cites W2736237086 @default.
• W3042512022 cites W2745005623 @default.
• W3042512022 cites W2750384547 @default.
• W3042512022 cites W2783525259 @default.
• W3042512022 cites W2798878556 @default.
• W3042512022 cites W2898323475 @default.
• W3042512022 cites W2922002199 @default.
• W3042512022 cites W2944910788 @default.
• W3042512022 cites W2963089565 @default.
• W3042512022 cites W2963966976 @default.
• W3042512022 cites W2964296416 @default.
• W3042512022 cites W2964299589 @default.
• W3042512022 cites W2970793768 @default.
• W3042512022 cites W2971489542 @default.
• W3042512022 cites W2974275398 @default.
• W3042512022 cites W3038988173 @default.
• W3042512022 cites W3090384356 @default.
• W3042512022 cites W3091431973 @default.
• W3042512022 cites W3091443325 @default.
• W3042512022 cites W3092582417 @default.
• W3042512022 cites W3099544558 @default.
• W3042512022 cites W3103266921 @default.
• W3042512022 cites W2006370340 @default.
• W3042512022 hasPublicationYear "2020" @default.
• W3042512022 type Work @default.
• W3042512022 sameAs 3042512022 @default.
• W3042512022 citedByCount "1" @default.
• W3042512022 countsByYear W30425120222021 @default.
• W3042512022 crossrefType "posted-content" @default.
• W3042512022 hasAuthorship W3042512022A5030422145 @default.
• W3042512022 hasAuthorship W3042512022A5057618925 @default.
• W3042512022 hasConcept C111919701 @default.
• W3042512022 hasConcept C11731999 @default.
• W3042512022 hasConcept C119599485 @default.
• W3042512022 hasConcept C119857082 @default.
• W3042512022 hasConcept C127413603 @default.
• W3042512022 hasConcept C138236772 @default.
• W3042512022 hasConcept C154945302 @default.
• W3042512022 hasConcept C159919123 @default.
• W3042512022 hasConcept C170493617 @default.
• W3042512022 hasConcept C185592680 @default.
• W3042512022 hasConcept C190502265 @default.
• W3042512022 hasConcept C25274449 @default.
• W3042512022 hasConcept C2742236 @default.
• W3042512022 hasConcept C2776214188 @default.
• W3042512022 hasConcept C41008148 @default.
• W3042512022 hasConcept C50644808 @default.
• W3042512022 hasConcept C55493867 @default.
• W3042512022 hasConcept C79974875 @default.
• W3042512022 hasConceptScore W3042512022C111919701 @default.
• W3042512022 hasConceptScore W3042512022C11731999 @default.
• W3042512022 hasConceptScore W3042512022C119599485 @default.
• W3042512022 hasConceptScore W3042512022C119857082 @default.
• W3042512022 hasConceptScore W3042512022C127413603 @default.
• W3042512022 hasConceptScore W3042512022C138236772 @default.
• W3042512022 hasConceptScore W3042512022C154945302 @default.
• W3042512022 hasConceptScore W3042512022C159919123 @default.
• W3042512022 hasConceptScore W3042512022C170493617 @default.
• W3042512022 hasConceptScore W3042512022C185592680 @default.
• W3042512022 hasConceptScore W3042512022C190502265 @default.
• W3042512022 hasConceptScore W3042512022C25274449 @default.
• W3042512022 hasConceptScore W3042512022C2742236 @default.
• W3042512022 hasConceptScore W3042512022C2776214188 @default.
• W3042512022 hasConceptScore W3042512022C41008148 @default.
• W3042512022 hasConceptScore W3042512022C50644808 @default.
• W3042512022 hasConceptScore W3042512022C55493867 @default.
• W3042512022 hasConceptScore W3042512022C79974875 @default.
• W3042512022 hasLocation W30425120221 @default.
• W3042512022 hasOpenAccess W3042512022 @default.
• W3042512022 hasPrimaryLocation W30425120221 @default.
• W3042512022 hasRelatedWork W2783304281 @default.
• W3042512022 hasRelatedWork W2802512292 @default.
• W3042512022 hasRelatedWork W2897802248 @default.
• W3042512022 hasRelatedWork W2902404732 @default.
• W3042512022 hasRelatedWork W2920117305 @default.
• W3042512022 hasRelatedWork W2922002199 @default.
• W3042512022 hasRelatedWork W2947161672 @default.
• W3042512022 hasRelatedWork W2971541781 @default.
• W3042512022 hasRelatedWork W2992556487 @default.

• next