AMNED: An Efficient Framework for Spiking Neuron Coding in AirComp Federated Learning

This paper advances ACFL technologies by proposing the Adaptive Memristor Neuron Encoding-Decoding (AMNED) framework for AirComp Federated Learning (ACFL), enabling efficient, privacy-preserving model aggregation optimized for resource-constrained wireless environments. In advancing future ACFL tech...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE access Ročník 13; s. 138970 - 138985
Hlavní autoři:	Ji, Juncheng, Lam, Chan-Tong, Wang, Ke, Ng, Benjamin K.
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	Piscataway IEEE 2025 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Adaptation models adaptive memristor neuron encoding-decoding framework Atmospheric modeling Computation Computational modeling Constraints Decoding Devices Efficiency Encoding Encoding-Decoding Energy Energy consumption Energy sources Energy utilization Federated learning internet of things low power consumption Machine learning Memristors Neural networks Neurons Over-the-air computation Privacy Sensors Signal reconstruction Spiking spiking neuron Superposition (mathematics) Wireless communication Wireless sensor networks
ISSN:	2169-3536, 2169-3536
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Buďte první, kdo okomentuje tento záznam!