2026· Journal of Network and Information Security· Vol 14, pp. 51-63· 0 citations
TL;DR
Results indicate that homeostatic threshold regulation offers a structurally non-invasive route to improved inference energy in gradient-trained SNNs.
Abstract
Spiking Neural Networks (SNNs) represent a biologically grounded computational paradigm in which information is carried by discrete spike events, conferring structural compatibility with low-power, event-driven neuromorphic hardware. A persistent impediment to realising the full energy benefit of SNNs in practice is the near-universal adoption of fixed firing thresholds, which prevent individual neurons from self-regulating their activity and permit task-irrelevant spike generation to accumulate unchecked. This paper introduces and evaluates a Homeostatically Regulated Adaptive Threshold (HAT) mechanism in which each neuron’s firing threshold is updated at every time step in proportion to the deviation between its exponentially smoothed firing rate and a designer-specified target rate. The rule is derived from the proportional control framework and mirrors the intrinsic excitability regulation observed in biological cortical circuits. A novel metric, the Target Achievement Error (TAE), is defined to quantify how faithfully the population reaches its intended operating point. Computational cost is assessed using a synaptic operations (SynOps) proxy that is hardware-agnostic and scales linearly with spike volume. A two-stage screening procedure selects the best configurations from 27 candidates by first enforcing an accuracy constraint and then ranking them by spike reduction, TAE, energy, and accuracy. Controlled experiments on MNIST show that the fixed-threshold baseline attains a mean validation accuracy of 92.52%±1.13% across three random seeds, with an average of 21.86 × 106 spikes and an estimated SynOps energy of 211.70 mJ. The top-ranked homeostatic configuration (α = 0.1, ftarget = 0.1, γ = 0.2) achieves 92.02% validation accuracy with a 15.54% reduction in total spike activity, incurring only a 0.50% absolute accuracy shortfall. These results indicate that homeostatic threshold regulation offers a structurally non-invasive route to improved inference energy in gradient-trained SNNs.
This work proposes Burst Spiking Neural Networks (BuSNNs), built upon Burst-enhanced Spiking Neurons and a Dynamic Weight Constraint (DWC) mechanism, which mitigates perturbation-induced transitions in activation states and thereby enhances robustness.
Jiahong Zhang, Sijun Shen, Man Yao et al.· 0 citations
This work presents a Hebbian local learning rule that models synaptic modification as a function of calcium traces tracking neuronal activity and demonstrates how spike timing and rate can be complementary in their role of shaping the connectivity of spiking neural networks.
Willian Soares Girāo, Nicoletta Risi, Caroline Geisler et al.· Neuromorphic Computing and E...· 0 citations
Biological neural systems achieve high efficiency and robustness through compartmentalized architectures. In contrast, modern artificial neural networks rely on globally entangled structures, which obscure decision logic and suffer from catastrophic forgetting. Here, we report a Decomposable Spiking Neural Network (D-SNN) that eliminates global synaptic entanglement by structurally isolating classification pathways into independent experts. Optimized via a bio-inspired push-pull loss function, the D-SNN achieves competitive accuracies on MNIST, Fashion-MNIST, and CIFAR-10/100 benchmarks. This modular approach matches the performance of fully dense networks while utilizing an order of magnitude fewer parameters. In addition, our networks operate with up to several orders of magnitude lower firing rates and fewer synaptic operations. Furthermore, physically severing connections between experts provides inherent protection against catastrophic forgetting during sequential learning. Crucially, these isolated pathways generate auditable neural signals, increasing decision transparency. This biomimetic, verifiable architecture establishes an efficient foundation for deploying deterministic neuromorphic intelligence in resource-constrained edge environments.
Maksim Bazhenov, S. Grubas, V. Putkaradze· 0 citations
Phenomenological spiking neuron models such as Izhikevich, adaptive quadratic integrate-and-fire (aQIF), and Adaptive Exponential (AdEx) are widely used because of their simplicity and numerical efficiency. These models reproduce diverse neuronal dynamics through a slow self-inhibitory adaptation variable. Here we introduce their symmetric counterpart by replacing adaptation with slow self-excitation, motivated by intrinsic calcium-mediated membrane currents. This minimal modification enables robust persistent spiking and working-memory dynamics without compromising computational efficiency. These properties remain in excitatory spiking neural networks. We then derive and validate a mean-field neural mass model that remains stable while retaining working-memory functionality. Additionally, we implement the single-neuron model in a minimal memristor-based neuromorphic circuit and experimentally confirm its dynamics. These results provide scalable tools for large-scale brain simulations and neuromorphic applications in robotics, brain-machine interfaces, and edge AI devices.
D. Depannemaecker, Adrien D’hollande, G. Casagrande et al.· Nature Communications· 0 citations
Real-time closed-loop neuromodulation, in which stimulation is precisely timed to ongoing brain dynamics, holds transformative potential for treating neurological disorders and probing neural circuit function. However, it requires low-latency, energy-efficient processing of high-bandwidth neural signals that conventional computing architectures struggle to deliver. Neuromorphic computing, which emulates the event-driven and massively parallel operation of biological neural circuits, offers a compelling alternative. Yet, its integration into closed-loop frameworks validated in vivo for fast, transient oscillations has not been demonstrated. Here, we present a fully integrated neuromorphic framework for real-time detection and manipulation of hippocampal ripples: brief (30-100 ms), high-frequency (100-250 Hz) oscillations that are critical for memory consolidation and implicated in neurological disorders. We train compact spiking neural networks comprising 41 neurons and 530 parameters using surrogate-gradient backpropagation, achieving detection performance competitive with deep learning models across 23 recording sessions while consuming up to 200-fold less energy when deployed on SpiNNaker neuromorphic hardware. Integration with the open-source Open Ephys platform yields total closed-loop latencies of approximately 50 ms, enabling intra-event stimulation in up to 80% of ripples. Validating the complete sensing-processing-stimulation pipeline in awake, head-fixed mice, we demonstrate that neuromorphic-triggered optogenetic inhibition significantly alters ripple dynamics and reduces oscillatory energy. This work establishes a practical and accessible neuromorphic framework for low-latency closed-loop control of fast brain dynamics in vivo.
P. Félix, M. Jurado-Parras, J. Freitas et al.· bioRxiv· 0 citations
We introduce a hardware circuit model that implements spike-time dependent plasticity (STDP) to endow spiking neural networks with learning capabilities. Our circuit model is characterized as both minimal and bio-inspired, due to its simplicity and to a novel active dendrite compartment that mimics the synaptic potentiation mechanism. The active dendrite consists of an integrate-and-fire stage which produces a train of pulses whose number is inversely related to the timing between pre- and post-synaptic spikes. The dendrite pulses modulate in a reliable manner the synaptic efficacy (conductance) that we implemented with a digipot, considered as an idealized non-volatile memristor. We demonstrate the behavior of the circuit by implementing a minimal spiking neuron model of associative learning by STDP, which is analog to the classic conditioning experiment of Pavlov’s dog.
Adrien D’hollande, Olivier Schneegans, Kang Wang et al.· Neuromorphic Computing and E...· 0 citations