Spiking Neural Networks with Consistent Mapping Relations Allow High-Accuracy Inference

TL;DR

This paper introduces a novel conversion framework for spiking neural networks that minimizes errors and delays, enabling high-accuracy inference with improved efficiency in neuromorphic hardware.

Contribution

The authors propose the CASC framework with the CIF neuron model and WSC method, achieving near loss-free conversion and reducing time delays in deep SNNs.

Findings

Significantly reduces conversion errors and delays.

Achieves high accuracy in classification and object detection.

Enhances the efficiency of neuromorphic inference.

Abstract

Spike-based neuromorphic hardware has demonstrated substantial potential in low energy consumption and efficient inference. However, the direct training of deep spiking neural networks is challenging, and conversion-based methods still require substantial time delay owing to unresolved conversion errors. We determine that the primary source of the conversion errors stems from the inconsistency between the mapping relationship of traditional activation functions and the input-output dynamics of spike neurons. To counter this, we introduce the Consistent ANN-SNN Conversion (CASC) framework. It includes the Consistent IF (CIF) neuron model, specifically contrived to minimize the influence of the stable point's upper bound, and the wake-sleep conversion (WSC) method, synergistically ensuring the uniformity of neuron behavior. This method theoretically achieves a loss-free conversion, markedly diminishing time delays and improving inference performance in extensive classification and object detection tasks. Our approach offers a viable pathway toward more efficient and effective neuromorphic systems.