Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387609330> ?p ?o ?g. }
Showing items 1 to 68 of
68
with 100 items per page.
- W4387609330 endingPage "12" @default.
- W4387609330 startingPage "1" @default.
- W4387609330 abstract "Performing symbol detection for multiple-input and multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) systems is challenging and resource-consuming. In this paper, we present a liquid state machine (LSM), a type of reservoir computing based on spiking neural networks (SNNs), to achieve energy-efficient and sustainable symbol detection on the Loihi chip for MIMO-OFDM systems. SNNs are more biological-plausible and energy-efficient than conventional deep neural networks (DNN) but have lower performance in terms of accuracy. To enhance the accuracy of SNNs, we propose a knowledge distillation training algorithm called DNN-SNN co-learning, which employs a bi-directional learning path between a DNN and an SNN. Specifically, the knowledge from the output and intermediate layer of the DNN is transferred to the SNN, and we exploit a decoder to convert the spikes in the intermediate layers of an SNN into real numbers to enable communication between the DNN and the SNN. Through the bi-directional learning path, the SNN can mimic the behavior of the DNN by learning the knowledge from the DNN. Conversely, the DNN can better adapt itself to the SNN by using the knowledge from the SNN. We introduce a new loss function to enable knowledge distillation on regression tasks. Our LSM is implemented on Intel's Loihi neuromorphic chip, a specialized hardware platform for SNN models. The experimental results on symbol detection in MIMO-OFDM systems demonstrate that our LSM on the Loihi chip is more precise than conventional symbol detection algorithms. Also, the model consumes approximately 6 times less energy per sample than other quantized DNN-based models with comparable accuracy." @default.
- W4387609330 created "2023-10-14" @default.
- W4387609330 creator A5013979759 @default.
- W4387609330 creator A5018632091 @default.
- W4387609330 creator A5018880777 @default.
- W4387609330 date "2023-01-01" @default.
- W4387609330 modified "2023-10-14" @default.
- W4387609330 title "DNN-SNN Co-Learning for Sustainable Symbol Detection in 5 G Systems on Loihi Chip" @default.
- W4387609330 doi "https://doi.org/10.1109/tsusc.2023.3324339" @default.
- W4387609330 hasPublicationYear "2023" @default.
- W4387609330 type Work @default.
- W4387609330 citedByCount "0" @default.
- W4387609330 crossrefType "journal-article" @default.
- W4387609330 hasAuthorship W4387609330A5013979759 @default.
- W4387609330 hasAuthorship W4387609330A5018632091 @default.
- W4387609330 hasAuthorship W4387609330A5018880777 @default.
- W4387609330 hasConcept C105795698 @default.
- W4387609330 hasConcept C113775141 @default.
- W4387609330 hasConcept C11731999 @default.
- W4387609330 hasConcept C118524514 @default.
- W4387609330 hasConcept C119599485 @default.
- W4387609330 hasConcept C127413603 @default.
- W4387609330 hasConcept C134400042 @default.
- W4387609330 hasConcept C151927369 @default.
- W4387609330 hasConcept C154945302 @default.
- W4387609330 hasConcept C165005293 @default.
- W4387609330 hasConcept C186370098 @default.
- W4387609330 hasConcept C199360897 @default.
- W4387609330 hasConcept C2742236 @default.
- W4387609330 hasConcept C33923547 @default.
- W4387609330 hasConcept C41008148 @default.
- W4387609330 hasConcept C50644808 @default.
- W4387609330 hasConcept C76155785 @default.
- W4387609330 hasConceptScore W4387609330C105795698 @default.
- W4387609330 hasConceptScore W4387609330C113775141 @default.
- W4387609330 hasConceptScore W4387609330C11731999 @default.
- W4387609330 hasConceptScore W4387609330C118524514 @default.
- W4387609330 hasConceptScore W4387609330C119599485 @default.
- W4387609330 hasConceptScore W4387609330C127413603 @default.
- W4387609330 hasConceptScore W4387609330C134400042 @default.
- W4387609330 hasConceptScore W4387609330C151927369 @default.
- W4387609330 hasConceptScore W4387609330C154945302 @default.
- W4387609330 hasConceptScore W4387609330C165005293 @default.
- W4387609330 hasConceptScore W4387609330C186370098 @default.
- W4387609330 hasConceptScore W4387609330C199360897 @default.
- W4387609330 hasConceptScore W4387609330C2742236 @default.
- W4387609330 hasConceptScore W4387609330C33923547 @default.
- W4387609330 hasConceptScore W4387609330C41008148 @default.
- W4387609330 hasConceptScore W4387609330C50644808 @default.
- W4387609330 hasConceptScore W4387609330C76155785 @default.
- W4387609330 hasLocation W43876093301 @default.
- W4387609330 hasOpenAccess W4387609330 @default.
- W4387609330 hasPrimaryLocation W43876093301 @default.
- W4387609330 hasRelatedWork W2756276189 @default.
- W4387609330 hasRelatedWork W2960220682 @default.
- W4387609330 hasRelatedWork W3089892344 @default.
- W4387609330 hasRelatedWork W4205804651 @default.
- W4387609330 hasRelatedWork W4287758233 @default.
- W4387609330 hasRelatedWork W4288055417 @default.
- W4387609330 hasRelatedWork W4312992603 @default.
- W4387609330 hasRelatedWork W4313442939 @default.
- W4387609330 hasRelatedWork W4372267706 @default.
- W4387609330 hasRelatedWork W4386227293 @default.
- W4387609330 isParatext "false" @default.
- W4387609330 isRetracted "false" @default.
- W4387609330 workType "article" @default.