Sparsifying Spiking Networks through Local Rhythms
This addresses energy efficiency for spiking neural networks, but it appears incremental as it builds on known sparsity in neural networks and applies local rhythms.
The paper tackles the problem of energy consumption in spiking neural networks by preventing the transmission of spikes representing near-zero values using local rhythms, which reduces communication and computation energy while preserving accuracy.
It has been well-established that within conventional neural networks, many of the values produced at each layer are zero. In this work, I demonstrate that spiking neural networks can prevent the transmission of spikes representing values close to zero using local information. This can reduce the amount of energy required for communication and computation in these networks while preserving accuracy. Additionally, this demonstrates a novel application of biologically observed spiking rhythms.