Spiking neural networks on FPGA: A survey of methodologies and recent advancements by Mehrzad Karamimanesh instant download

Spiking neural networks on FPGA: A survey of methodologies and recent advancements by Mehrzad Karamimanesh instant download

B S T R A C TKeywords:The mimicry of the biological brain’s structure in information processing enables spiking neural networksSpiking neural network(SNNs) to exhibit significantly reduced power consumption compared to conventional systems. Consequently,Neuromorphic computingthese networks have garnered heightened attention and spurred extensive research endeavors in recent years,Field-programmable gate arrayproposing various structures to achieve low power consumption, high speed, and improved recognition ability.Brain-inspired computingHowever, researchers are still in the early stages of developing more efficient neural networks that more closelyAcceleratorresemble the biological brain. This development and research require suitable hardware for execution withappropriate capabilities, and field-programmable gate array (FPGA) serves as a highly qualified candidatecompared to existing hardware such as central processing unit (CPU) and graphics processing unit (GPU).FPGA, with parallel processing capabilities similar to the brain, lower latency and power consumption, andhigher throughput, is highly eligible hardware for assisting in the development of spiking neural networks. Inthis review, an attempt has been made to facilitate researchers’ path to further develop this field by collectingand examining recent works and the challenges that hinder the implementation of these networks on FPGA.Contents