$SpikePack$: Enhanced Information Flow in Spiking Neural Networks with High Hardware Compatibility

TL;DR

${SpikePack}$ is a novel neuron model that enhances information flow in SNNs, enabling efficient GPU processing, better accuracy, and hardware compatibility for diverse applications.

Contribution

Introduces ${SpikePack}$, a neuron model with constant complexity that improves information transmission, supports efficient parallel processing, and enables high-performance SNN deployment across hardware.

Findings

Achieves significant accuracy improvements in image tasks.

Enables efficient GPU-based SNN processing.

Demonstrates cross-platform hardware compatibility.

Abstract

Spiking Neural Networks (SNNs) hold promise for energy-efficient, biologically inspired computing. We identify substantial informatio loss during spike transmission, linked to temporal dependencies in traditional Leaky Integrate-and-Fire (LIF) neuron-a key factor potentially limiting SNN performance. Existing SNN architectures also underutilize modern GPUs, constrained by single-bit spike storage and isolated weight-spike operations that restrict computational efficiency. We introduce ${SpikePack}$, a neuron model designed to reduce transmission loss while preserving essential features like membrane potential reset and leaky integration. ${SpikePack}$ achieves constant $\mathcal{O}(1)$ time and space complexity, enabling efficient parallel processing on GPUs and also supporting serial inference on existing SNN hardware accelerators. Compatible with standard Artificial Neural Network (ANN) architectures, ${SpikePack}$ facilitates near-lossless ANN-to-SNN conversion across various networks. Experimental results on tasks such as image classification, detection, and segmentation show ${SpikePack}$ achieves significant gains in accuracy and efficiency for both directly trained and converted SNNs over state-of-the-art models. Tests on FPGA-based platforms further confirm cross-platform flexibility, delivering high performance and enhanced sparsity. By enhancing information flow and rethinking SNN-ANN integration, ${SpikePack}$ advances efficient SNN deployment across diverse hardware platforms.