Energy-Aware Spike Budgeting for Continual Learning in Spiking Neural Networks for Neuromorphic Vision

TL;DR

This paper introduces an energy-aware spike budgeting framework for continual learning in spiking neural networks, enhancing accuracy and reducing power consumption across various neuromorphic vision datasets.

Contribution

It presents a novel spike budgeting approach that jointly optimizes accuracy and energy efficiency in continual SNN learning, with adaptive mechanisms tailored for different data modalities.

Findings

Spike budgeting improves accuracy on frame-based datasets by up to 17.45 percentage points.

Spike rates are reduced by up to 47% on certain datasets, decreasing power consumption.

Method demonstrates consistent performance gains across five neuromorphic vision benchmarks.

Abstract

Neuromorphic vision systems based on spiking neural networks (SNNs) offer ultra-low-power perception for event-based and frame-based cameras, yet catastrophic forgetting remains a critical barrier to deployment in continually evolving environments. Existing continual learning methods, developed primarily for artificial neural networks, seldom jointly optimize accuracy and energy efficiency, with particularly limited exploration on event-based datasets. We propose an energy-aware spike budgeting framework for continual SNN learning that integrates experience replay, learnable leaky integrate-and-fire neuron parameters, and an adaptive spike scheduler to enforce dataset-specific energy constraints during training. Our approach exhibits modality-dependent behavior: on frame-based datasets (MNIST, CIFAR-10), spike budgeting acts as a sparsity-inducing regularizer, improving accuracy while reducing spike rates by up to 47\%; on event-based datasets (DVS-Gesture, N-MNIST, CIFAR-10-DVS), controlled budget relaxation enables accuracy gains up to 17.45 percentage points with minimal computational overhead. Across five benchmarks spanning both modalities, our method demonstrates consistent performance improvements while minimizing dynamic power consumption, advancing the practical viability of continual learning in neuromorphic vision systems.