2023/08/16 by Bin Lei, Lei, Bin, Sheng Lin +7
Computer Science · Engineering · Neuroscience · #Advanced Memory and Neural Computing #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Neural Networks and Reservoir Computing #Neural and Evolutionary Computing (cs.NE) #Neural dynamics and brain function
paper · pdf · doi:10.48550/arxiv.2308.08649
openalex publication_date 2023/08/16 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Biologically-inspired Spiking Neural Networks (SNNs), processing information using discrete-time events known as spikes rather than continuous values, have garnered significant attention due to their hardware-friendly and energy-efficient characteristics. However, the training of SNNs necessitates a considerably large memory footprint, given the additional storage requirements for spikes or events, leading to a complex structure and dynamic setup. In this paper, to address memory constraint in SNN training, we introduce an innovative framework, characterized by a remarkably low memory footprint. We (i) design a reversible SNN node that retains a high level of accuracy. Our design is able to achieve a 58.65× reduction in memory usage compared to the current SNN node. We (ii) propose a unique algorithm to streamline the backpropagation process of our reversible SNN node. This significantly trims the backward Floating Point Operations Per Second (FLOPs), thereby accelerating the training process in comparison to current reversible layer backpropagation method. By using our algorithm, the training time is able to be curtailed by 23.8% relative to existing reversible layer architectures.