2026· Computers, Materials & Continua· Vol 88, pp. 1-10· 0 citations· 34 references
TL;DR
A Rate-Coded Cross-Attention (RCCA) module is proposed, which converts population-coded spike-trains into attention queries, allowing long-range dependency modeling within sub-milliwatt (sub-mW) power budgets.
Abstract
: Conventional deep learning networks impose prohibitive energy requirements on continuously operational network intelligence applications such as anomaly detection, traffic classification, and adaptive Quality-of-Service (QoS) control. This paper proposes NeuroPulse, a spiking-transformer hybrid neural architecture that combines the temporal sparsity of spiking neural networks (SNNs) with the representational power of sparse self-attention, enabling efficient deployment on neuromorphic network processors (NNPs). We propose a Rate-Coded Cross-Attention (RCCA) module, which converts population-coded spike-trains into attention queries, allowing long-range dependency modeling within sub-milliwatt (sub-mW) power budgets. NeuroPulse also supports catastrophe-free continual learning on non-stationary network traffic distributions via a Hebbian Synaptic Consolidation (HSC) mechanism, eliminating the need for full model retraining. Experiments on NSL-KDD, UNSW-NB15, and real-world 5G RAN telemetry datasets demonstrate that NeuroPulse achieves 94.3% intrusion detection accuracy at 0.23 mW average energy consumption—a 12 × power reduction over transformer-only baselines—while retaining 97.1% of accumulated knowledge after 50 sequential task updates, making it uniquely suited for always-on intelligent network nodes.
Spiking Neural Networks (SNNs) enable event-driven computation with sparse activations, but building multimodal Transformers on SNNs is hindered by unstable training in deep spiking stacks and the mismatch between dense softmax attention and spike-based communication. We propose SMM Transformer, an SNN-based multimodal Transformer framework that combines (i)PLMP, a Parallel LIF with Multistage Learnable Parameters neuron and a tailored P-STBP algorithm for stable deep SNN training, (ii) SMSA, an attention-inspired spike-driven token-mixing module that replaces dense pairwise softmax attention with channel-wise spike co-activation and self-compensation, and (iii)SMoE, a spiking mixture-of-experts module for modality-aware fusion. Across visual and multimodal benchmarks, SMM Transformer achieves competitive accuracy compared to ANN baselines. Under a standard MAC/AC arithmetic model, SMSA reduces the estimated operator-level compute energy of the attention module by up to 97%, while whole-model profiling shows more moderate but consistent efficiency gains.
Xiubo Liang, Jinxing Han, Yuke Li et al.· 0 citations
It is aimed at proving that SNNs have potential in such areas as computer vision, robotics, and speech recognition, and their role in overcoming the barrier between artificial and biological neural systems is proved.
Mesala Sravani, K. Kumari, S. M. Reddy· International Journal of Unc...· 0 citations
Extensive experiments on static and neuromorphic benchmarks show that lower-bit BASC models match or outperform higher-bit baselines and retain this accuracy advantage after structured pruning, while further reducing model storage and synaptic operations.
Linliang Chen, Yan Zhong, Xin Liu et al.· 0 citations
Spiking Neural Networks (SNNs) often rely on rate coding, where high-precision inference depends on long time-steps, leading to significant latency and energy cost—especially for ANN-to-SNN conversions. To address this, we propose Adaptive Fission, a post-training encoding technique that selectively splits high-sensitivity neurons into groups with varying scales and weights. This enables neuron-specific, on-demand precision and threshold allocation while introducing minimal spatial overhead. As a generalized form of population coding, it seamlessly applies to a wide range of pretrained SNN architectures without requiring additional training or fine-tuning. Experiments on neuromorphic hardware demonstrate up to 80% reductions in latency and power consumption without degrading accuracy.
Yizhou Jiang, Feng Chen, Yihan Li et al.· Neural Information Processin...· 2 citations
Deploying anomaly detection models on energy constrained industrial platforms is an open and pivotal challenge for manufacturing. This paper presents ALPS (Anomaly detection with Low Power Spiking neural networks), a lightweight neuro-morphic pipeline for acoustic fault classification in a reciprocating air compressor. Raw audio waveforms are decomposed by a 16-channel band pass filter bank and converted into spike trains, which are then processed by a feed-forward spiking neural network with one hidden layer composed of 128 leaky integrate-and-fire neurons. The full pipeline is deployed on the SynSense Xylo Audio 3 neuromorphic processor after 7-bit post-training quantization. On an eight-class benchmark dataset, the system achieves 0.93 macro F1 while consuming only 3.4 mW, roughly three orders of magnitude less than a 1D convolutional neural network running on a Raspberry Pi 4 at comparable accuracy. A robustness study with structured additive factory noise shows graceful performance degradation and no abrupt collapse. These results demonstrate that neuromorphic hardware is a viable, ultra-low-power alternative for always-on acoustic anomaly detection at the edge.
F. Aisa, Umberto Albertin, Mauro Martini et al.· 2026 IEEE/ASME International...· 0 citations
Spiking neural networks offer a promising route toward low-power sequence computation on neuromorphic hardware, but they continue to lag behind attention-based artificial neural networks on long-context tasks. A central open question is whether this gap reflects only implementation and optimization limitations, or whether architectural features of spiking computation impose unfavorable learnability constraints as sequence length increases. Here, we address this question using a covering-number analysis of feedforward non-leaky integrate-and-fire (nLIF) networks in the probably approximately correct framework. Building on causal-piece decompositions and local Lipschitz continuity, we derive a global sensitivity bound for feedforward nLIF networks and extend it from single-token inputs to multi-token spike sequences. For fixed architectures under stated boundedness and margin assumptions, the resulting sufficient worst-case sample requirement has leading quadratic dependence on sequence length. This dependence arises from cumulative causal participation across time and depth, which increases global sensitivity along active spike paths. We then test the mechanistic implications of this theory using finite-sample cue-recall and teacher–student benchmarks across spiking, recurrent, and attention-based model classes. In cue-recall, an early cue must be retained across distractors and reported at a final query token; in teacher–student, labels are generated by a fixed nLIF teacher, separating representability from finite-sample learnability. Unconstrained feedforward spiking models show sequence-length sensitivity, elevated hidden spike-participation density, and increased samples-to-threshold burden. Post-spike refractoriness, leak-mediated forgetting, learned lateral inhibition, and activity-constrained winner-take-all competition reduce hidden participation and improve empirical robustness in task- and regime-dependent ways. Together, these results identify diffuse causal-set growth as a fundamental architectural bottleneck for baseline feedforward spiking sequence models and suggest that scalable neuromorphic sequence architectures will require circuit mechanisms that explicitly constrain temporal accumulation and effective spike participation.
William Fishell, Gordon Fishell, Suraj Honnuraiah· Neuromorphic Computing and E...· 0 citations