Gradient-Free Continual Learning in Spiking Neural Networks via Inter-Spike Interval Regularization

2026-04-13

AI Summary

This work addresses the challenge that existing gradient-based continual learning methods are incompatible with neuromorphic hardware lacking backpropagation support, thereby failing to achieve truly forgetting-free sequential learning. The authors propose ISI-CV, a novel gradient-free approach that introduces, for the first time, a synaptic importance metric based on the coefficient of variation of interspike intervals (ISI). This mechanism identifies regularly firing neurons to preserve previously acquired knowledge while permitting irregularly firing neurons to adapt to new tasks. Relying solely on spike-timing counts and integer arithmetic, ISI-CV is inherently compatible with diverse neuromorphic chips. The method achieves zero forgetting (AF = 0.000) on Split-MNIST and Split-FashionMNIST and sets new state-of-the-art results on the real-world DVS dataset N-MNIST, attaining the highest average accuracy (AA = 0.820) and the lowest forgetting (AF = 0.221).

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Computer Vision: Learning & Optimization for CV
• Machine Learning: Neuro-Symbolic Learning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Continual learning, the ability to acquire new tasks sequentially without forgetting prior knowledge, is essential for deploying neural networks in dynamic real-world environments, from nuclear digital twin monitoring to grid-edge fault detection. Existing synaptic importance methods, such as Elastic Weight Consolidation (EWC) and Synaptic Intelligence (SI), rely on gradient computation, making them incompatible with neuromorphic hardware that lacks backpropagation support. We propose ISI-CV, the first gradient-free synaptic importance metric for SNN continual learning, derived from the Coefficient of Variation (CV) of Inter-Spike Intervals (ISIs). Neurons that fire regularly (low CV) encode stable, task-relevant features and are protected from overwriting; neurons with irregular firing are permitted to adapt freely. ISI-CV requires only spike time counters and integer arithmetic, all of which are native to every neuromorphic chip. We evaluate on four benchmarks of increasing difficulty: Split-MNIST, Permuted-MNIST, Split-FashionMNIST, and Split-N-MNIST using real Dynamic Vision Sensor (DVS) event data. Across three seeds, ISI-CV achieves zero forgetting (AF = 0.000 +/- 0.000) on Split-MNIST and Split-FashionMNIST, near-zero forgetting on Permuted-MNIST (AF = 0.001 +/- 0.000), and the highest accuracy with the lowest forgetting on real neuromorphic DVS data (AA = 0.820 +/- 0.012, AF = 0.221 +/- 0.014). On N-MNIST, gradient-based methods produce unreliable importance estimates and perform worse than no regularization; ISI-CV avoids this failure by design.

Problem

• Continual Learning
• Spiking Neural Networks
• Gradient-Free
• Neuromorphic Hardware
• Synaptic Importance

Innovation

• gradient-free
• spiking neural networks
• continual learning
• inter-spike interval
• neuromorphic computing