General aspects of internal noise in spiking neural networks

TL;DR

This paper investigates how different types and sources of noise affect spiking neural networks, identifying key noise mechanisms and proposing filtering strategies to enhance robustness.

Contribution

It systematically analyzes the impact of additive and multiplicative noise at various neural processing stages and evaluates filtering methods to mitigate performance degradation.

Findings

Multiplicative noise on membrane potential most degrades accuracy.

Sigmoid-based input filtering improves robustness against noise.

SNNs are more robust to common noise than to independent noise.

Abstract

This study examines the impact of additive and multiplicative noise on both a single leaky integrate-and-fire (LIF) neuron and a trained spiking neural network (SNN). Noise was introduced at different stages of neural processing, including the input current, membrane potential, and output spike generation. The results show that multiplicative noise applied to the membrane potential has the most detrimental effect on network performance, leading to a significant degradation in accuracy. This is primarily due to its tendency to suppress membrane potentials toward large negative values, effectively silencing neuronal activity. To address this issue, input pre-filtering strategies were evaluated, with a sigmoid-based filter demonstrating the best performance by shifting inputs to a strictly positive range. Under these conditions, additive noise in the input current becomes the dominant source of performance degradation, while other noise configurations reduce accuracy by no more than 1\%, even at high noise intensity. Additionally, the study compares the effects of common and uncommon noise across neuron populations in hidden layer, revealing that SNNs exhibit greater robustness to common noise. Overall, the findings identify the most critical noise mechanisms affecting SNNs and provide practical approaches for improving their robustness.