A Comprehensive Review of Spiking Neural Networks: Interpretation, Optimization, Efficiency, and Best Practices
This is an incremental review paper that synthesizes existing knowledge for researchers and practitioners interested in low-power, mobile, or hardware-constrained AI applications.
The paper tackles the under-investigated area of biologically plausible, energy-efficient spiking neural networks by presenting a comprehensive literature review of recent developments in interpretation, optimization, efficiency, and accuracy, with a focus on making the field accessible to new practitioners.
Biological neural networks continue to inspire breakthroughs in neural network performance. And yet, one key area of neural computation that has been under-appreciated and under-investigated is biologically plausible, energy-efficient spiking neural networks, whose potential is especially attractive for low-power, mobile, or otherwise hardware-constrained settings. We present a literature review of recent developments in the interpretation, optimization, efficiency, and accuracy of spiking neural networks. Key contributions include identification, discussion, and comparison of cutting-edge methods in spiking neural network optimization, energy-efficiency, and evaluation, starting from first principles so as to be accessible to new practitioners.