All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Selective Alignment Kd SnnSeAl-KD methodology for SNN knowledge distillation that selectively aligns class-level and temporal knowledge. Equalizes competing logits at erroneous timesteps and reweights temporal alignment based on confidence and inter-timestep similarity. Works on static images and neuromorphic event-based datasets.Votes: 0GitHub stars: 3
- Selfdistillation Learning Based On Temporalspatial Consistency For Spiking Neural Networks**arXiv ID:** 2406.07862 **Authors:** Lin Zuo, Yongqi Ding, Mengmeng Jing, Kunshan Yang, Yunqian Yu **Published:** 2024-06-12T04:30:40Z **Abstract:** Spiking neural networks (SNNs) have attracted considerable attention for their event-driven, low-power characteristics and high biological interpretability. Inspired by knowledge distillation (KD), recent research has improved the performance of the SNN model with a pre-trained teacher model. However, additional teacher models require significan...Votes: 0GitHub stars: 3
- Sequence Learning Using Equilibrium Propagation**arXiv ID:** 2209.09626 **Authors:** Malyaban Bal, Abhronil Sengupta **Published:** 2022-09-14T20:01:22Z **Abstract:** Equilibrium Propagation (EP) is a powerful and more bio-plausible alternative to conventional learning frameworks such as backpropagation. The effectiveness of EP stems from the fact that it relies only on local computations and requires solely one kind of computational unit during both of its training phases, thereby enabling greater applicability in domains such as bio-ins...Votes: 0GitHub stars: 3
- Sequence Timing Snn ReplaySpiking neural network methodology for learning sequence timing and controlling replay speed through STDP-based temporal encoding.Votes: 0GitHub stars: 3
- Shiftequivariant Similaritypreserving Hypervector Representations Of Sequences**arXiv ID:** 2112.15475 **Authors:** Dmitri A. Rachkovskij **Published:** 2021-12-31T14:29:12Z **Abstract:** Hyperdimensional Computing (HDC), also known as Vector-Symbolic Architectures (VSA), is a promising framework for the development of cognitive architectures and artificial intelligence systems, as well as for technical applications and emerging neuromorphic and nanoscale hardware. HDC/VSA operate with hypervectors, i.e., distributed vector representations of large fixed dimension (usu...Votes: 0GitHub stars: 3
- Shiftlif Efficient Multilevel Spiking Neurons With Poweroftwo Quantization**arXiv ID:** 2605.01866 **Authors:** Kaiwen Tang, Di Yu, Jiaqi Zheng, Changze Lv, Qianhui Liu, Zhanglu Yan, Weng-Fai Wong **Published:** 2026-05-03T13:20:53Z **Abstract:** Spiking neural networks (SNNs) are promising for edge sensing due to their event-driven computation and temporal filtering capability. However, standard leaky integrate-and-fire (LIF) neurons communicate only through binary spikes, which severely limit representational capacity. Existing multi-level spiking neurons improve...Votes: 0GitHub stars: 3
- Signn A Spikeinduced Graph Neural Network For Dynamic Graph Representation Learning**arXiv ID:** 2404.07941 **Authors:** Dong Chen, Shuai Zheng, Muhao Xu, Zhenfeng Zhu, Yao Zhao **Published:** 2024-03-11T05:19:43Z **Abstract:** In the domain of dynamic graph representation learning (DGRL), the efficient and comprehensive capture of temporal evolution within real-world networks is crucial. Spiking Neural Networks (SNNs), known as their temporal dynamics and low-power characteristic, offer an efficient solution for temporal processing in DGRL task. However, owing to the spike...Votes: 0GitHub stars: 3
- Silif Dbs Neuromorphic ControllerNeuromorphic Silicon Neuron Controller for Adaptive Deep Brain Stimulation in Parkinson's Disease - CMOS-implemented SiLIF-DBS controller achieving 5.85%/uW beta suppression efficiency with 75% power reduction vs open-loopVotes: 0GitHub stars: 3
- Simple And Complex Spiking Neurons Perspectives And Analysis In A Simple Stdp Scenario**arXiv ID:** 2207.04881 **Authors:** Davide Liberato Manna, Alex Vicente Sola, Paul Kirkland, Trevor Bihl, Gaetano Di Caterina **Published:** 2022-06-28T10:01:51Z **Abstract:** Spiking neural networks (SNNs) are largely inspired by biology and neuroscience and leverage ideas and theories to create fast and efficient learning systems. Spiking neuron models are adopted as core processing units in neuromorphic systems because they enable event-based processing. The integrate-and-fire (I&F) mode...Votes: 0GitHub stars: 3
- Single Entity Spiking Neuron Models SurveyIn this work, we reviewed different approaches in mathematical modeling of biologically plausible neural systems. Models are characterized and classified based on their common features and special use. Based on arXiv:2607.07429.Votes: 0GitHub stars: 3
- Snn Beyond Dales PrincipleCollective dynamics in spiking neural networks beyond Dale's principle. Mixed excitatory-inhibitory neurons. Activation: dale's principle, mixed neurons, collective dynamics, excitatory inhibitory, snn dynamics.Votes: 0GitHub stars: 3
- Snn Complexity Classification脉冲神经网络复杂度分类方法论。使用Lempel-Ziv复杂度（LZC）评估SNN分类性能，比较不同神经元模型（LIF、元神经元、Levy-Baxter）和学习规则（STDP、tempotron）。适用于生物信号处理、SNN架构选择、脉冲序列分析。触发词：脉冲神经网络、SNN、Lempel-Ziv复杂度、神经元模型、STDP、LIF、spiking neural network、complexity classification。Votes: 0GitHub stars: 3
- Snn Eeg Alzheimer Biophysical SignaturesLearning Alzheimer's disease biophysical signatures via EEG and Spiking Neural Networks. Combines biophysical modeling of neurodegeneration with SNN-based biomarker extraction from EEG signals. Simulates AD pathology effects on neural circuits and learns discriminative signatures. Activation: Alzheimer, EEG biomarker, spiking neural network, neurodegeneration, AD detection, biophysical simulation.Votes: 0GitHub stars: 3
- Snn Elephant ReinforcementSpiking Neural Networks with Elephant Reinforcement — finite stochastic spiking-neuron network where past firing activity modifies future excitability through reinforcement-dependent threshold.Votes: 0GitHub stars: 3
- Snn Fpga Hardware Software CodesignFPGA accelerator design for Spiking Neural Networks using Spiking Recurrent Cell (SRC) neurons, with mathematical simplifications to remove costly unary operators and avoid floating-point arithmetic. Covers piecewise approximations, LUT-register weight storage, and accuracy/energy trade-off analysis. Use when deploying SNNs on FPGA hardware, designing neuromorphic accelerators, or optimizing SNN inference energy efficiency. Trigger: SNN FPGA, spiking recurrent cell, SRC neuron, neuromorphic h...Votes: 0GitHub stars: 3
- Snn Heterogeneous Delay Working MemoryWorking memory implementation in recurrent spiking neural networks using heterogeneous synaptic delays. Enables energy-efficient neuromorphic storage and recall of precise temporal spike patterns.Votes: 0GitHub stars: 3
- Snn Heterogeneous Synaptic DelaysWorking memory implementation in recurrent spiking neural networks using heterogeneous synaptic delays. Biological approach to memory with variable delay timescales. Activation: working memory, synaptic delays, recurrent snn, heterogeneous delays, neural memory.Votes: 0GitHub stars: 3
- Snn Internal Noise Analysis V2Internal noise analysis in Spiking Neural Networks examining how intrinsic noise affects network dynamics, computation, and learning. Covers noise sources, propagation effects, and computational benefits. Trigger words: internal noise, SNN noise, spiking noise, intrinsic noise, stochastic dynamics.Votes: 0GitHub stars: 3
- Snn Learning NeuromorphicSpiking Neural Network learning methods for neuromorphic computing — covering surrogate gradient, STDP, three-factor learning, DECOLLE, and sharpness-aware training. Use when training SNNs on neuromorphic hardware, implementing event-based learning, optimizing sparsity in spiking networks, or deploying energy-efficient AI. Trigger words: spiking neural network, SNN training, surrogate gradient, STDP, three-factor learning, DECOLLE, neuromorphic learning, event-based learning, temporal credit ...Votes: 0GitHub stars: 3
- Snn Learning Rules DynamicsSNN learning rules, dynamics, and learning ability analysis methodology. Covers Hebbian/anti-Hebbian learning, reward-based learning, backpropagation, surrogate gradients, and their relationships to network dynamics.Votes: 0GitHub stars: 3
- Snn Multimodal BrainBrain-Inspired Multimodal Spiking Neural Network for Image-Text Retrieval. Activation: braininspired, multimodal, spiking, imagetext, retrievalVotes: 0GitHub stars: 3
- Snn Neuromorphic Fpga... 触发词: neuromorphic, spiking, snnVotes: 0GitHub stars: 3
- Snn Quantization Beyond AccuracyQuantization of Spiking Neural Networks beyond accuracy - evaluating SNN quantization using Earth Mover's Distance (EMD) and firing distribution preservation, not just task accuracy.Votes: 0GitHub stars: 3
- Snn Quantization Emd Beyond AccuracyEarth Mover's Distance (EMD) framework for evaluating SNN quantization beyond accuracy. Shows uniform quantization causes firing distribution drift even when accuracy is preserved. Proposes LQ-Net style learned quantization for maintaining firing behavior.Votes: 0GitHub stars: 3
- Snn Reconstruction Autapse基于论文 'Reconstructing Spiking Neural Networks Using a Single Neuron with Autapses' 的神经科学研究方法论。arXiv:2603.24692v1Votes: 0GitHub stars: 3
- Snn Reconstruction AutapsesReconstructing spiking neural networks using a single neuron with autapses. Topology inference from single-neuron dynamics. Activation: snn reconstruction, autapses, network topology, single neuron, reverse engineering.Votes: 0GitHub stars: 3
- Snn Safety Thresholds Automated DrivingBiologically-inspired reinterpretation of Surrogate Safety Measures (SSMs) using LIF neuron spiking thresholds. SNN combines multiple SSM inputs to emit spikes aligned with human braking onsets, capturing sustained borderline conditions and high-risk peaks better than fixed thresholds. Use when: autonomous driving safety, SSM thresholds, LIF neurons, spiking neural networks, car-following, braking behavior, traffic risk evaluation, human safety perception, temporal sensitivity. Activation: sa...Votes: 0GitHub stars: 3
- Snn Self Adaptation Robustness CapacityNeuronal Self-Adaptation Enhances Capacity and Robustness of Representation in Spiking Neural Networks. Activation: neuronal, selfadaptation, enhances, capacity, robustnessVotes: 0GitHub stars: 3
- Snn Simulation Tools ReviewSNN Simulation Tools ReviewVotes: 0GitHub stars: 3
- Snn Topology SimulationTopology-exploiting optimization for brain-scale spiking neural network simulations — reducing communication bottlenecks via network-aware compute node assignment and dynamic load balancing.Votes: 0GitHub stars: 3
- Snn Working Memory Heterogeneous Delays V4Recurrent SNN with heterogeneous synaptic delays for working memory. Weight tensor W∈R^{N×N×D} with D=41 delays per synapse, trained via surrogate gradient BPTT. Spiking Motifs concept achieves F1=1.0 on M=16 patterns with N=512 neurons.Votes: 0GitHub stars: 3
- Social Spatial Dependencies For Learning Visual NavigationNavigation for social organisms rarely is a fully independent activity. Group structure and dynamics, as well as embodied interactions, critically influence useful behavior. Individual neural network. Based on arXiv:2607.07460.Votes: 0GitHub stars: 3
- Soliton Waves Wstdp SnnSoliton-like waves in 2D recurrent spiking neural networks with weighted STDP - biologically plausible discrete-time neuron model combining multiplicative STDP, divisive normalization, and homeostatic threshold adaptation to generate stable wave propagation.Votes: 0GitHub stars: 3
- Spear Structured Pruning For Spiking Neural Networks Via Synaptic Operation Estimation And Reinforcement Learning**arXiv ID:** 2507.02945 **Authors:** Hui Xie, Yuhe Liu, Shaoqi Yang, Jinyang Guo, Yufei Guo, Yuqing Ma, Jiaxin Chen, Jiaheng Liu, Xianglong Liu **Published:** 2025-06-28T15:21:05Z **Abstract:** While deep spiking neural networks (SNNs) demonstrate superior performance, their deployment on resource-constrained neuromorphic hardware still remains challenging. Network pruning offers a viable solution by reducing both parameters and synaptic operations (SynOps) to facilitate the edge deployment ...Votes: 0GitHub stars: 3
- Spectral Theory Population Density Spiking NeuronsSpectral theory framework for analyzing population density dynamics of spiking neurons with refractoriness. Provides rigorous mathematical foundation for spectral decomposition methods in computational neuroscience by formulating the problem as a non-self-adjoint boundary eigenvalue problem for the Fokker-Planck operator.Votes: 0GitHub stars: 3
- Spectral Theory Spiking Neurons RefractorinessSpectral theory framework for analyzing population density dynamics of spiking neurons with refractoriness. Provides rigorous operator-theoretic methods for studying neuronal population dynamics, spectral characterization of Fokker-Planck operators, and transfer function derivation for networks with absolute refractory periods. Use when analyzing spiking neural network stability, oscillatory modes, or refractory effects on population dynamics.Votes: 0GitHub stars: 3
- Spikebased Neuromorphic Computing For Nextgeneration Computer Vision**arXiv ID:** 2310.09692 **Authors:** Md Sakib Hasan, Catherine D. Schuman, Zhongyang Zhang, Tauhidur Rahman, Garrett S. Rose **Published:** 2023-10-15T01:05:35Z **Abstract:** Neuromorphic Computing promises orders of magnitude improvement in energy efficiency compared to traditional von Neumann computing paradigm. The goal is to develop an adaptive, fault-tolerant, low-footprint, fast, low-energy intelligent system by learning and emulating brain functionality which can be realized through i...Votes: 0GitHub stars: 3
- Spikemllm Multimodal SpikingSpikeMLLM: First spike-based Multimodal Large Language Model (MLLM) framework. Unifies ANN quantization methods into spike representation space via Modality-Specific Temporal Scales (MSTS) and Temporal Compression LIF (TC-LIF) neurons. Compresses timestep from T=L-1 to T=log2(L)-1 while maintaining near-lossless performance across four MLLMs. Enables energy-efficient multimodal inference through spike-based computation. 首个基于脉冲的多模态大语言模型框架，通过模态特定时间尺度和时间压缩LIF神经元实现高效多模态推理。Votes: 0GitHub stars: 3
- Spikeprophecy BenchmarkSpikeProphecy benchmark methodology for autoregressive neural population forecasting. From paper 'SpikeProphecy: A Large-Scale Benchmark for Autoregressive Neural Population Forecasting' (arXiv: 2605.12992). Introduces a benchmark suite pairing four neural datasets (mouse, rat, macaque) with task-specific evaluation protocols covering causal structure, latent recovery, forecasting accuracy, and behavioral readout dimensions. Use when: evaluating neural population models, spike forecasting ben...Votes: 0GitHub stars: 3
- Spiker Ll Fpga Snn AcceleratorSpiker-LL methodology — FPGA-based SNN accelerator enabling adaptive local learning at the edge. Extends the open-source Spiker+ inference architecture with efficient support for the Spiking Time Sparse Feedback (STSF) local learning rule. Achieves up to 93% accuracy (MNIST/F-MNIST/DIGITS), sub-millisecond latency, and <0.1 mJ per inference, remaining DSP-free and highly scalable for edge-FPGA deployments. Use when: designing edge SNN hardware accelerators, implementing on-device learning, bu...Votes: 0GitHub stars: 3
- Spikerl A Scalable And Energyefficient Framework For Deep Spiking Reinforcement Learning**arXiv ID:** 2502.17496 **Authors:** Tokey Tahmid, Mark Gates, Piotr Luszczek, Catherine D. Schuman **Published:** 2025-02-21T05:28:42Z **Abstract:** In this era of AI revolution, massive investments in large-scale data-driven AI systems demand high-performance computing, consuming tremendous energy and resources. This trend raises new challenges in optimizing sustainability without sacrificing scalability or performance. Among the energy-efficient alternatives of the traditional Von Neumann...Votes: 0GitHub stars: 3
- Spiking Approximations Of The Maxpooling Operation In Deep Snns**arXiv ID:** 2205.07076 **Authors:** Ramashish Gaurav, Bryan Tripp, Apurva Narayan **Published:** 2022-05-14T14:47:10Z **Abstract:** Spiking Neural Networks (SNNs) are an emerging domain of biologically inspired neural networks that have shown promise for low-power AI. A number of methods exist for building deep SNNs, with Artificial Neural Network (ANN)-to-SNN conversion being highly successful. MaxPooling layers in Convolutional Neural Networks (CNNs) are an integral component to downsampl...Votes: 0GitHub stars: 3
- Spiking Bandpass Wavelet EncodingSpiking Bandpass Wavelet encoding methodology for temporal signal representation. Recasts spike encoders as time-causal wavelet frames with quantitative bandwidths and resolution guarantees. Connects neuromorphic spike encoding with classical signal processing via bandpass wavelet decomposition. Use when: spike encoding, temporal signal encoding, wavelet-based spiking, neuromorphic encoding, event-based temporal representation, bandpass filtering with spikes, signal processing for SNNs, time-...Votes: 0GitHub stars: 3
- Spiking Bandpass Wavelet EncodingSpiking Bandpass Wavelet encoding methodology for temporal signal processing using spike-based representations. Recasts spike encoders as time-causal wavelet frames with quantitative bandwidths and reconstruction error bounds. Preserves sparsity and locality of spiking representations, with direct mapping to neuromorphic hardware. Use when: spike-based signal encoding, neuromorphic signal processing, spiking wavelet transforms, temporal signal encoding/decoding, energy-efficient spike encodin...Votes: 0GitHub stars: 3
- Spiking Brain Complex NetworksSpiking neural networks modeling on complex brain networks. Combines SNN dynamics with realistic brain connectivity to study neural dynamics and brain function. (arXiv:2604.07361, 2026-04)Votes: 0GitHub stars: 3
- Spiking Connectome Hierarchical State SpaceThis work presents the Parallelized Hierarchical Connectome (PHC), a general framework that upgrades temporal-only State-Space Models (SSMs) into spatiotemporal recurrent networks.... Activation: spiking neural network, connectome, state-space modelVotes: 0GitHub stars: 3
- Spiking Generative Networks StpSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Spiking Nerf Neuromorphic VisionBio-inspired spike-based Neural Radiance Fields (NeRF) for neuromorphic vision systems using Spiking Neural NetworksVotes: 0GitHub stars: 3
- Spiking Neural Architecture SearchNeural Architecture Search (NAS) methodology for Spiking Neural Networks (SNNs). Covers search spaces, strategies, evaluation methods, and performance optimization. Based on arXiv:2604.16889 (April 2026).Votes: 0GitHub stars: 3
- Spiking Neural Network AnalysisAnalyze Spiking Neural Network (SNN) papers, extract technical patterns from knowledge graph, and identify reusable research methodologies for neuromorphic computing.Votes: 0GitHub stars: 3