spike-based temporal classification

This work addresses binary classification of multivariate time series on resource-constrained edge devices, specifically under stringent low-false-alarm-rate requirements for incremental prediction. Method: We propose a lightweight spiking neural network (SNN) framework optimized via the Evolutionary Optimization of Neural Spiking (EONS) algorithm, jointly evolving both architecture and parameters to yield an ultra-sparse, stateful SNN with only 49 neurons. Input is encoded via spike-based representation, and classification employs a single-neuron spike-count decision mechanism, enhanced by simple voting-based ensemble for robustness. Contribution/Results: To our knowledge, this is the first efficient deployment of an SNN on the microCaspian neuromorphic platform. On gamma-ray spectroscopy data, it achieves 67.1% true positive rate (TPR) at a false alarm rate of 1/hr—substantially outperforming PCA- and deep learning–based baselines. For EEG-based epileptic seizure detection, it attains 95% TPR while reducing parameter count by over 90%.

To address the challenge of simultaneously achieving biological plausibility, hardware efficiency, and competitive performance in spiking neural networks (SNNs) for general supervised classification, this paper proposes a columnar hierarchical SNN architecture tailored for classification. It employs intra-class-difference-driven columnar organization—each column represents a discriminative subcategory—and adopts an all-spiking signal flow with functionally specialized neurons. A biologically grounded learning mechanism is introduced, integrating local anti-Hebbian plasticity with dopamine neuromodulation to replace backpropagation entirely. The method unifies model-driven reinforcement learning with a state-proximity evaluation framework, enabling end-to-end training directly in the spike domain. Experiments demonstrate that the architecture achieves high accuracy and strong generalization across multiple benchmark classification tasks, while exhibiting exceptional compatibility with low-power neuromorphic hardware. This work establishes a novel paradigm for practical, deployable SNNs.

Spiking Neural Networks (SNNs) face a fundamental trade-off between accuracy and efficiency due to non-differentiable spiking dynamics, strong temporal dependencies, and event-driven sparsity. To address this, we propose a biologically inspired classification framework that integrates Lempel–Ziv Complexity (LZC) with SNNs—marking the first incorporation of LZC-based structural complexity analysis into SNN learning, thereby enabling explicit accuracy–efficiency optimization. We systematically evaluate biologically plausible learning rules (e.g., tempotron, Spikprop) and ANN-to-SNN conversion methods on real-time spatiotemporal neural data, identifying their practical applicability boundaries. Experiments demonstrate that tempotron and Spikprop achieve >90% of classical backpropagation accuracy on image and neural signal classification tasks, while reducing computational overhead by approximately two orders of magnitude and enabling millisecond-scale online inference. This yields substantial improvements in interpretability and hardware deployment feasibility.

This work addresses the fundamental challenge in spiking neural networks (SNNs) of reconciling convolutional weight sharing with the biological constraint of local synaptic plasticity. To this end, we propose a biologically inspired convolutional SNN architecture for image classification. Our method comprises two key components: (1) employing fixed, pre-defined convolutional kernels for feedforward feature extraction—thereby preserving locality in spike-timing-dependent plasticity (STDP) or other local learning rules—and (2) introducing a data-driven initialization strategy based on domain-specific image sets to enhance both the biological plausibility and discriminative power of the initial kernels. Evaluated on the NEOVISION2 benchmark, our approach significantly improves feature representation capability and inference efficiency while maintaining high classification accuracy and strong biological interpretability. To the best of our knowledge, this is the first demonstration that a fixed convolutional structure can be effectively co-optimized with spiking dynamics to achieve competitive performance, thereby validating a novel paradigm for biologically grounded deep SNN design.

Existing theoretical analyses of spiking neural networks (SNNs) lack quantitative characterizations of their universal representational capacity as sequence-to-sequence processors over spike trains. Method: We propose a function approximation framework grounded in spike-train modeling, integrating constructive weight design with rigorous temporal complexity quantification. Contribution/Results: We establish the first constructively provable, near-optimal universal approximation theorem for naturally spikable function classes—i.e., functions admitting efficient spike-based realization. Theorematically, SNNs achieve near-optimal complexity in both neuron count and synaptic weight count. They exhibit significant representational advantages for sparse inputs, low-order temporal functions, and composite functions. Moreover, our analysis provides rigorous theoretical foundations for modular deep SNN architectures and downstream tasks such as spike-sequence classification.

Traditional artificial neural networks (ANNs) suffer from low energy efficiency and slow dynamic response, limiting their suitability for edge and neuromorphic computing. Method: This study systematically investigates modeling and training mechanisms of leaky integrate-and-fire (LIF) spiking neural networks (SNNs) for brain-inspired computing. We propose a multi-strategy comparative framework integrating surrogate gradient descent, ANN-to-SNN conversion, and spike-timing-dependent plasticity (STDP), evaluated across accuracy, energy consumption (mJ/inference), latency (ms), and convergence epochs. Results: Surrogate gradient training achieves near-ANN accuracy (within 1–2% degradation), converges by epoch 20, and attains inference latency as low as 10 ms; STDP yields ultra-low energy consumption (5 mJ/inference), enabling unsupervised learning and ultra-low-power edge deployment. This work quantitatively characterizes, for the first time, the fundamental trade-offs among accuracy, energy efficiency, and latency across SNN training paradigms—providing a deployable optimization roadmap for robotic perception, neuromorphic vision, and edge AI.

This work addresses the challenge of efficiently training event-driven spiking neural networks (SNNs), which is hindered by the sequential nature of hard-reset dynamics and the absence of a differentiable, temporally continuous method for precise spike-time computation. To overcome these limitations, the authors propose a parallel associative scan algorithm that enables, for the first time, simultaneous processing of multiple spikes in native event-based SNNs. Combined with a machine-precision differentiable spike-time solver, this approach preserves the continuous-time hard-reset dynamics while eliminating reliance on time binning. Evaluated on four event-based datasets, the method achieves up to a 44-fold speedup over conventional sequential simulation, demonstrating both superior computational efficiency and high temporal precision in spike timing.

Directly training spiking neural networks (SNNs) on static images leads to temporal collapse and hinders effective modeling of spatiotemporal dynamics, as conventional time encoding schemes—e.g., repeated frame presentation—induce rate-coding bias rather than exploiting rich temporal structure. Method: We propose a learnable phase-shift temporal encoding mechanism that maps static images to spike trains with adaptive timing patterns. Crucially, we decouple encoding design from network optimization, revealing that convolutional layer learnability and surrogate gradient formulation—not the encoding itself—are the primary determinants of performance. Accordingly, we design a minimal, end-to-end trainable temporal encoder. Results: Our approach significantly narrows the accuracy gap between direct and rate coding, preserves the energy efficiency of SNNs, and enhances spatiotemporal feature representation. It establishes a new paradigm for efficient, temporally expressive modeling of static images in SNNs.

Spiking neural networks (SNNs) suffer from limited performance on visual tasks, primarily due to inadequate information representation in conventional spike encoding schemes and poor compatibility with surrogate gradient-based training. To address this, we propose the first hybrid time-bit spike encoding framework designed explicitly for end-to-end surrogate gradient training. Our method decomposes input images into bit planes and applies temporal coding—such as latency or phase coding—to each bit plane, yielding a joint rate-time representation. Crucially, the entire encoding process is differentiable, enabling stable and efficient backpropagation via surrogate gradients. This design substantially enhances spatiotemporal information capacity and gradient propagation stability. Extensive experiments on CIFAR-10/100 and ImageNet-1K demonstrate that SNNs trained with our framework match or surpass state-of-the-art encoding methods—including rate coding, time-to-first-spike (TTFS), and spike-time coding—in accuracy, validating its effectiveness, generalizability, and seamless integration with standard surrogate-gradient optimization pipelines.

This work addresses the limitations of neural prosthetic control—namely high latency, excessive power consumption, and communication bandwidth bottlenecks—that hinder device usability and patient mobility. To overcome these challenges, the authors propose an event-driven, efficient neural decoding approach that, for the first time, integrates event-driven gated recurrent units with sparse hierarchical spiking encoding to enable on-chip decoding with minimal communication overhead and low power consumption. By leveraging sparse inference and an efficient training strategy, the method achieves task performance comparable to or better than conventional spiking neural networks while substantially reducing computational and energetic demands. This advancement offers a practical, high-performance deployment solution for wearable neural prosthetics with significantly lower resource requirements.