TMN: A Lightweight Neuron Model for Efficient Nonlinear Spike Representation

TL;DR

The paper introduces TMN, a lightweight neuron model that enhances nonlinear spike representation in SNNs, enabling high-precision encoding with fewer timesteps and improved scalability for practical deployment.

Contribution

TMN features a novel momentum mechanism and ternary predictive scheme, offering a scalable, hardware-friendly neuron model for efficient spike encoding in SNNs.

Findings

Achieves high-precision encoding with fewer timesteps

Demonstrates scalability across diverse tasks and architectures

Provides a hardware-aware solution for SNN computing

Abstract

Spike trains serve as the primary medium for information transmission in Spiking Neural Networks, playing a crucial role in determining system efficiency. Existing encoding schemes based on spike counts or timing often face severe limitations under low-timestep constraints, while more expressive alternatives typically involve complex neuronal dynamics or system designs, which hinder scalability and practical deployment. To address these challenges, we propose the Ternary Momentum Neuron (TMN), a novel neuron model featuring two key innovations: (1) a lightweight momentum mechanism that realizes exponential input weighting by doubling the membrane potential before integration, and (2) a ternary predictive spiking scheme which employs symmetric sub-thresholds $\pm\frac{1}{2}v_{th}$ to enable early spiking and correct over-firing. Extensive experiments across diverse tasks and network architectures demonstrate that the proposed approach achieves high-precision encoding with significantly fewer timesteps, providing a scalable and hardware-aware solution for next-generation SNN computing.