Average-Over-Time Spiking Neural Networks for Uncertainty Estimation in Regression

TL;DR

This paper introduces two novel methods for uncertainty estimation in regression using Average-Over-Time Spiking Neural Networks, demonstrating competitive performance and energy efficiency compared to traditional deep learning models.

Contribution

The paper adapts the AOT-SNN framework for regression tasks, proposing heteroscedastic Gaussian and Regression-as-Classification methods for improved uncertainty estimation.

Findings

AOT-SNN models perform comparably or better than state-of-the-art methods.

The methods provide reliable uncertainty estimates in regression tasks.

The approaches are energy-efficient and biologically inspired.

Abstract

Uncertainty estimation is a standard tool to quantify the reliability of modern deep learning models, and crucial for many real-world applications. However, efficient uncertainty estimation methods for spiking neural networks, particularly for regression models, have been lacking. Here, we introduce two methods that adapt the Average-Over-Time Spiking Neural Network (AOT-SNN) framework to regression tasks, enhancing uncertainty estimation in event-driven models. The first method uses the heteroscedastic Gaussian approach, where SNNs predict both the mean and variance at each time step, thereby generating a conditional probability distribution of the target variable. The second method leverages the Regression-as-Classification (RAC) approach, reformulating regression as a classification problem to facilitate uncertainty estimation. We evaluate our approaches on both a toy dataset and several benchmark datasets, demonstrating that the proposed AOT-SNN models achieve performance comparable to or better than state-of-the-art deep neural network methods, particularly in uncertainty estimation. Our findings highlight the potential of SNNs for uncertainty estimation in regression tasks, providing an efficient and biologically inspired alternative for applications requiring both accuracy and energy efficiency.