Agreeing to Stop: Reliable Latency-Adaptive Decision Making via Ensembles of Spiking Neural Networks

TL;DR

This paper introduces ensemble-based uncertainty estimation for spiking neural networks, enabling more reliable and faster early decisions in time series classification with theoretical guarantees.

Contribution

It proposes a novel ensemble approach with information pooling for SNNs that improves latency and reliability over existing methods, supported by theoretical guarantees.

Findings

Ensemble models improve decision reliability in SNNs.

The method reduces average latency compared to state-of-the-art.

The approach maintains theoretical reliability guarantees.

Abstract

Spiking neural networks (SNNs) are recurrent models that can leverage sparsity in input time series to efficiently carry out tasks such as classification. Additional efficiency gains can be obtained if decisions are taken as early as possible as a function of the complexity of the input time series. The decision on when to stop inference and produce a decision must rely on an estimate of the current accuracy of the decision. Prior work demonstrated the use of conformal prediction (CP) as a principled way to quantify uncertainty and support adaptive-latency decisions in SNNs. In this paper, we propose to enhance the uncertainty quantification capabilities of SNNs by implementing ensemble models for the purpose of improving the reliability of stopping decisions. Intuitively, an ensemble of multiple models can decide when to stop more reliably by selecting times at which most models agree that the current accuracy level is sufficient. The proposed method relies on different forms of information pooling from ensemble models, and offers theoretical reliability guarantees. We specifically show that variational inference-based ensembles with p-variable pooling significantly reduce the average latency of state-of-the-art methods, while maintaining reliability guarantees.