# Sleep-Based Homeostatic Regularization for Stabilizing Spike-Timing-Dependent Plasticity in Recurrent Spiking Neural Networks

arXiv: https://arxiv.org/abs/2601.08447 · HTML: https://mlsanity.com/paper/2601.08447/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 26 references that are in the map.
- First posted on arXiv 13 Jan 2026.

## Builds on (most cited first, 12 of 12)

- [Incorporating Learnable Membrane Time Constant to Enhance Learning of Spiking Neural Networks](https://mlsanity.com/paper/2007.05785/) (2020)
- [Deep Directly-Trained Spiking Neural Networks for Object Detection](https://mlsanity.com/paper/2307.11411/) (2023)
- [Gradient Descent for Spiking Neural Networks](https://mlsanity.com/paper/1706.04698/) (2017)
- [Exploiting Noise as a Resource for Computation and Learning in Spiking Neural Networks](https://mlsanity.com/paper/2305.16044/) (2023)
- [The Overfitted Brain: Dreams evolved to assist generalization](https://mlsanity.com/paper/2007.09560/) (2020)
- [Learning cortical representations through perturbed and adversarial dreaming](https://mlsanity.com/paper/2109.04261/) (2021)
- [Evolving Connectivity for Recurrent Spiking Neural Networks](https://mlsanity.com/paper/2305.17650/) (2023)
- [Directly Training Temporal Spiking Neural Network with Sparse Surrogate Gradient](https://mlsanity.com/paper/2406.19645/) (2024)
- [Sleep-like slow oscillations improve visual classification through synaptic homeostasis and memory association in a thalamo-cortical model](https://mlsanity.com/paper/1810.10498/) (2018)
- [Accelerating Sensor Fusion in Neuromorphic Computing: A Case Study on Loihi-2](https://mlsanity.com/paper/2408.16096/) (2024)
- [A wake-sleep algorithm for recurrent, spiking neural networks](https://mlsanity.com/paper/1703.06290/) (2017)
- [Making a Spiking Net Work: Robust brain-like unsupervised machine learning](https://mlsanity.com/paper/2208.01204/) (2022)

## Built on by (most cited first, 1 of 1)

- [Exploring napping paradigm for Recurrent Spiking Neural Networks](https://mlsanity.com/paper/2609.13927/) (2026)

## Abstract (arXiv)

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.