dorsal/arxiv
View SchemaSleep-Based Homeostatic Regularization for Stabilizing Spike-Timing-Dependent Plasticity in Recurrent Spiking Neural Networks
| Authors | Andreas Massey, Aliaksandr Hubin, Stefano Nichele, Solve Sæbø |
|---|---|
| Categories | |
| ArXiv ID | 2601.08447vv1 |
| URL | https://arxiv.org/abs/2601.08447 |
| License | http://creativecommons.org/licenses/by-nc-sa/4.0/ |
Abstract
Spike-timing-dependent plasticity (STDP) provides a biologically-plausible learning mechanism for spiking neural networks (SNNs); however, Hebbian weight updates in architectures with recurrent connections suffer from pathological weight dynamics: unbounded growth, catastrophic forgetting, and loss of representational diversity. We propose a neuromorphic regularization scheme inspired by the synaptic homeostasis hypothesis: periodic offline phases during which external inputs are suppressed, synaptic weights undergo stochastic decay toward a homeostatic baseline, and spontaneous activity enables memory consolidation. We demonstrate that this sleep-wake cycle prevents weight saturation while preserving learned structure. Empirically, we find that low to intermediate sleep durations (10-20\% of training) improve stability on MNIST-like benchmarks in our STDP-SNN model, without any data-specific hyperparameter tuning. In contrast, the same sleep intervention yields no measurable benefit for the surrogate-gradient spiking neural network (SG-SNN). Taken together, these results suggest that periodic, sleep-based renormalization may represent a fundamental mechanism for stabilizing local Hebbian learning in neuromorphic systems, while also indicating that special care is required when integrating such protocols with existing gradient-based optimization methods.
{
"annotation_id": "e667e548-03b9-4dd9-83db-201d54930a3a",
"date_created": "2026-02-17T05:53:16.021000Z",
"date_modified": "2026-02-17T05:53:16.021000Z",
"file_hash": "8d9b9cc03ac3304ad6d14c26c6e998ff433c68a541c794ef14c890269a0b7ad0",
"private": false,
"record": {
"abstract": "Spike-timing-dependent plasticity (STDP) provides a biologically-plausible learning mechanism for spiking neural networks (SNNs); however, Hebbian weight updates in architectures with recurrent connections suffer from pathological weight dynamics: unbounded growth, catastrophic forgetting, and loss of representational diversity. We propose a neuromorphic regularization scheme inspired by the synaptic homeostasis hypothesis: periodic offline phases during which external inputs are suppressed, synaptic weights undergo stochastic decay toward a homeostatic baseline, and spontaneous activity enables memory consolidation. We demonstrate that this sleep-wake cycle prevents weight saturation while preserving learned structure. Empirically, we find that low to intermediate sleep durations (10-20\\% of training) improve stability on MNIST-like benchmarks in our STDP-SNN model, without any data-specific hyperparameter tuning. In contrast, the same sleep intervention yields no measurable benefit for the surrogate-gradient spiking neural network (SG-SNN). Taken together, these results suggest that periodic, sleep-based renormalization may represent a fundamental mechanism for stabilizing local Hebbian learning in neuromorphic systems, while also indicating that special care is required when integrating such protocols with existing gradient-based optimization methods.",
"arxiv_id": "2601.08447",
"authors": [
"Andreas Massey",
"Aliaksandr Hubin",
"Stefano Nichele",
"Solve S\u00e6b\u00f8"
],
"categories": [
"cs.NE",
"stat.ML"
],
"license": "http://creativecommons.org/licenses/by-nc-sa/4.0/",
"title": "Sleep-Based Homeostatic Regularization for Stabilizing Spike-Timing-Dependent Plasticity in Recurrent Spiking Neural Networks",
"url": "https://arxiv.org/abs/2601.08447",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "1e6f3171-2faa-4d22-9770-b0a3a7d58828",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}