Sigma-Delta Neural Network Conversion on Loihi 2

TL;DR

This paper introduces a novel method for converting traditional neural networks into spiking neural networks on Intel's Loihi 2 platform, leveraging graded spikes to improve efficiency and reduce simulation time compared to previous rate-based methods.

Contribution

The paper presents a new conversion technique utilizing Loihi 2's graded spikes, enabling more efficient and accurate SNNs by exploiting temporal and spatial sparsity.

Findings

Achieved improved efficiency over rate-based SNN conversions

Demonstrated competitive performance on Loihi 2 compared to NVIDIA Jetson Xavier

Reduced simulation time per inference using graded spikes

Abstract

Neuromorphic computing aims to improve the efficiency of artificial neural networks by taking inspiration from biological neurons and leveraging temporal sparsity, spatial sparsity, and compute near/in memory. Although these approaches have shown efficiency gains, training these spiking neural networks (SNN) remains difficult. The original attempts at converting trained conventional analog neural networks (ANN) to SNNs used the rate of binary spikes to represent neuron activations. This required many simulation time steps per inference, which degraded efficiency. Intel's Loihi 2 is a neuromorphic platform that supports graded spikes which can be used to represent changes in neuron activation. In this work, we use Loihi 2's graded spikes to develop a method for converting ANN networks to spiking networks, which take advantage of temporal and spatial sparsity. We evaluated the performance of this network on Loihi 2 and compared it to NVIDIA's Jetson Xavier edge AI platform.