Stochasticity and Robustness in Spiking Neural Networks

TL;DR

This paper explores how noise in synaptic weights affects spiking neural networks, demonstrating that inherent stochasticity can enhance robustness to inaccuracies, especially when using analog memory devices.

Contribution

It provides a mathematical analysis and experimental validation showing noise can improve robustness of spiking neural networks against synaptic inaccuracies.

Findings

Noisy networks are more robust to synaptic inaccuracy.

Noise can be leveraged to improve neural network robustness.

Resistive memory-based synapses benefit from inherent stochasticity.

Abstract

Artificial neural networks normally require precise weights to operate, despite their origins in biological systems, which can be highly variable and noisy. When implementing artificial networks which utilize analog 'synaptic' devices to encode weights, however, inherent limits are placed on the accuracy and precision with which these values can be encoded. In this work, we investigate the effects that inaccurate synapses have on spiking neurons and spiking neural networks. Starting with a mathematical analysis of integrate-and-fire (IF) neurons, including different non-idealities (such as leakage and channel noise), we demonstrate that noise can be used to make the behavior of IF neurons more robust to synaptic inaccuracy. We then train spiking networks which utilize IF neurons with and without noise and leakage, and experimentally confirm that the noisy networks are more robust. Lastly, we show that a noisy network can tolerate the inaccuracy expected when hafnium-oxide based resistive random-access memory is used to encode synaptic weights.