Optimal Conversion of Conventional Artificial Neural Networks to Spiking Neural Networks

TL;DR

This paper introduces a novel conversion pipeline that effectively transforms conventional ANNs into SNNs with minimal accuracy loss and significantly reduced simulation time, enhancing efficiency for neuromorphic hardware applications.

Contribution

The work presents a new layer-wise analysis of conversion error and a strategic weight transfer method combining threshold balance and soft-reset mechanisms.

Findings

Achieves near-zero accuracy loss in converted SNNs

Reduces SNN simulation time to about one-tenth of typical methods

Enhances suitability for embedded neuromorphic platforms

Abstract

Spiking neural networks (SNNs) are biology-inspired artificial neural networks (ANNs) that comprise of spiking neurons to process asynchronous discrete signals. While more efficient in power consumption and inference speed on the neuromorphic hardware, SNNs are usually difficult to train directly from scratch with spikes due to the discreteness. As an alternative, many efforts have been devoted to converting conventional ANNs into SNNs by copying the weights from ANNs and adjusting the spiking threshold potential of neurons in SNNs. Researchers have designed new SNN architectures and conversion algorithms to diminish the conversion error. However, an effective conversion should address the difference between the SNN and ANN architectures with an efficient approximation \DSK{of} the loss function, which is missing in the field. In this work, we analyze the conversion error by recursive reduction to layer-wise summation and propose a novel strategic pipeline that transfers the weights to the target SNN by combining threshold balance and soft-reset mechanisms. This pipeline enables almost no accuracy loss between the converted SNNs and conventional ANNs with only $\sim1/10$ of the typical SNN simulation time. Our method is promising to get implanted onto embedded platforms with better support of SNNs with limited energy and memory.