Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation

Understand

Spiking Neural Network (SNN) is a promising energy-efficient AI model when implemented on neuromorphic hardware.

• However, it is a challenge to efficiently train SNNs due to their non-differentiability.
• Most existing methods either suffer from high latency (i.e., long simulation time steps), or cannot achieve as high performance as Artificial Neural Networks (ANNs).
• In this paper, we propose the Differentiation on Spike Representation (DSR) method, which could achieve high performance that is competitive to ANNs yet with low latency.