All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Spike Ptsd AdversarialAdversarial robustness analysis for Spiking Neural Networks. Spike-Triggered Decoupled (SpikT) attack methodology exploiting temporal vulnerability and STDP-induced sensitivity. Covers vulnerability analysis, attack implementation, and defense strategies.Votes: 0GitHub stars: 3
- Spike Timing Neuronal Assemblies脉冲时序训练和自发强化神经元集群。研究STDP如何形成共享刺激偏好的强耦合神经元集群，自发动力学期间的脉冲相关性主动强化连接。适用于计算神经科学、STDP学习、神经编码研究。触发词：神经元集群、STDP、脉冲时序、神经编码、自发动力学、neuronal assembly、spike timing、STDP、noise correlation。Votes: 0GitHub stars: 3
- Spikedecoder Snn Gpt ArchitectureSpikeDecoder - Fully SNN-based implementation of Transformer decoder block for NLP applications, achieving 87-93% energy reduction while maintaining performanceVotes: 0GitHub stars: 3
- Spikenas A Fast Memoryaware Neural Architecture Search Framework For Spiking Neural Networkbased Embedded Ai Systems**arXiv ID:** 2402.11322 **Authors:** Rachmad Vidya Wicaksana Putra, Muhammad Shafique **Published:** 2024-02-17T16:33:54Z **Abstract:** Embedded AI systems are expected to incur low power/energy consumption for solving machine learning tasks, as these systems are usually power constrained (e.g., object recognition task in autonomous mobile agents with portable batteries). These requirements can be fulfilled by Spiking Neural Networks (SNNs), since their bio-inspired spike-based operations of...Votes: 0GitHub stars: 3
- Spiker Ll Fpga Snn AcceleratorSpiker-LL methodology: FPGA-based SNN accelerator enabling on-device adaptive local learning via STSF (Spiking Time Sparse Feedback) rule. Extends open-source Spiker+ inference architecture with hardware-adapted three-factor learning. Achieves 92-93% accuracy, sub-ms latency, <0.1mJ per inference, DSP-free. Use when: designing SNN hardware accelerators, implementing on-device learning, edge neuromorphic computing, STSF learning rule, FPGA SNN deployment, hardware-algorithm co-design, local le...Votes: 0GitHub stars: 3
- Spiker Ll Snn AcceleratorSPIKER-LL methodology for FPGA-accelerated adaptive local learning in Spiking Neural Networks. Extends Spiker+ inference architecture with STSF (Spike-Timing-Specific-Feedback) local learning rule support on FPGA. DSP-free, sub-millisecond latency, <0.1 mJ per inference. Enables on-device SNN training at the edge. Use when: designing FPGA SNN accelerators, implementing local learning rules in hardware, building edge AI systems with on-device learning, optimizing SNN inference/training latency...Votes: 0GitHub stars: 3
- Spikereg Snn Medical RegistrationSpikeReg: Energy-efficient 3D deformable medical image registration using Spiking Neural Networks with ANN-to-SNN conversion and surrogate gradient fine-tuning.Votes: 0GitHub stars: 3
- Spiketimer Snn Copyright ProtectionActive copyright protection for Spiking Neural Networks via temporal backdoor regularizationVotes: 0GitHub stars: 3
- Spikevla Spiking Vla Embodied NavigationPaper analysis: SpikeVLA — a spiking Vision-Language-Action architecture for embodied navigation with energy-efficient inference (ICML 2026). Replaces dense continuous layers with event-driven spiking layers across vision (Spike-V), language (Spike-L), and action (Spike-A) components. Achieves significant energy reduction while maintaining competitive performance on navigation and robotic control. Source: arXiv:2606.27807 (cs.RO), accepted ICML 2026, 2026-06-26. Activation keywords: SpikeVLA,...Votes: 0GitHub stars: 3
- Spiking Arm Locomotor CoordinationSpiking Neural Network architecture coordinating bipedal locomotion and arm control via NEF/SPA with biologically grounded basal ganglia for humanoid robotsVotes: 0GitHub stars: 3
- Spiking Bandpass Wavelet EncodingSpiking Bandpass Wavelet encoding methodology for temporal signal processing. Recasts spike encoders as time-causal wavelet frames with quantitative bandwidths and reconstruction error bounds. Maps spike representations to signal processing theory, enabling neuromorphic hardware implementation. Applicable to SNN temporal encoding, neuromorphic signal processing, event-based sensing, ECG/audio processing with spiking networks. Activation: spiking wavelet, spike encoding, temporal signal encodi...Votes: 0GitHub stars: 3
- Spiking Bandpass Wavelet EncodingSpiking Bandpass Wavelet encoding methodology for temporal signal encoding and decoding. Recasts spike encoders as time-causal wavelet frames with quantitative bandwidths and reconstruction error bounds. Maps directly to neuromorphic hardware. Applicable to spike-based encoding, temporal signal processing, neuromorphic computing, event-based sensing. Triggers: spike encoding, wavelet encoding, temporal signal processing, neuromorphic encoding, event-based signal reconstruction.Votes: 0GitHub stars: 3
- Spiking Compositional Neural OperatorSCNO (Spiking Compositional Neural Operator) — modular neuromorphic architecture combining spiking neurons with compositional neural operators for energy-efficient, incremental PDE solving.Votes: 0GitHub stars: 3
- Spiking Computational Neuroscience SurveyComprehensive survey of Spiking Neural Networks (SNNs) applied to computational neuroscience. Bridges the gap between artificial SNNs and biological neural computation, covering neuron models, learning rules, network architectures, and neuroscientific applications. Provides practical guide for using SNNs as computational models of brain function. Applicable to SNN neuroscience modeling, biologically plausible learning, neural simulation. Trigger: SNN computational neuroscience, biologically p...Votes: 0GitHub stars: 3
- Spiking Dynamic Neural Manifolds ImplementationConcrete implementation recipe for dynamic neural manifold control on neuromorphic hardware (SpiNNaker 2), derived from arXiv 2607.07373. Covers rate→spike conversion, sparse circulant weight memory, three control knobs (gain/speed, additive current/shape, subspace inhibition/selection), PCA-based manifold validation, and closed-loop maze navigation with linear readout training. Use when porting ring-attractor sequential SNNs to spike-based neuromorphic chips or building explainable low-dimen...Votes: 0GitHub stars: 3
- Spiking Ep Biologically Plausible TrainingEquilibrium Propagation (EP) with Predictive Learning in Leaky Integrate-and-Fire Spiking Neural Networks. Biologically plausible alternative to backpropagation for training SNNs using energy-based two-phase learning.Votes: 0GitHub stars: 3
- Spiking Event Driven Mamba AsrSpiking and Event-driven Neuromorphic Mamba Models for speech recognition. Achieves 60-70% activation sparsity with minimal accuracy loss on LibriSpeech. Introduces event-driven SpeechMamba with FATReLU and spiking SpeechMamba for hardware-efficient ASR.Votes: 0GitHub stars: 3
- Spiking Event Driven Neuromorphic Mamba AsrSpiking and Event-driven Neuromorphic Mamba Models for Efficient Speech Recognition — achieving 60-70% activation sparsity with minimal accuracy loss on ASR tasks.Votes: 0GitHub stars: 3
- Spiking Free Energy ControlSpiking neural network control framework based on the Free Energy Principle (FEP) and Active Inference. Neurons fire only when they reduce free energy of internal representation, achieving highly sparse activity with robust control. Matches performance of non-spiking frameworks while offering resilience against sensory noise, synaptic noise, delays, and neuron silencing. Use when designing spiking control systems, neuromorphic control algorithms, active inference with SNNs, energy-efficient r...Votes: 0GitHub stars: 3
- Spiking Memristor MultimodalMemristive neurons supporting multiple spiking functionalities (TTFS, spike count, firing rate) via annealing optimization for neuromorphic hardware.Votes: 0GitHub stars: 3
- Spiking Mllm Multimodal NeuromorphicSpiking Multimodal Large Language Model (SpikeMLLM) via Modality-Adaptive Transformer. Bridges gap between SNN and continuous neural networks for efficient multimodal AI. 10x energy reduction, 5x speedup on neuromorphic hardware. Applications: edge AI, neuromorphic vision-language, low-power multimodal systems.Votes: 0GitHub stars: 3
- Spiking Mode Neural Networks脉冲模式神经网络训练框架。基于Hopfield分解将循环权重矩阵分解为输入/输出模式和评分矩阵，显著降低训练成本，揭示低维吸引子结构。适用于神经形态计算、SNN训练加速、神经流形分析。触发词：脉冲模式网络、Hopfield分解、SNN训练加速、神经流形、spiking mode、Hopfield decomposition、neural manifold、attractor dynamics。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
- Spiking Neural Network Differential EquationDifferential equation analysis of SNN dynamics. Translates discrete spiking models into continuous ODE/PDE formulations for stability analysis, bifurcation study, and dynamical systems characterization. Activation: SNN differential equations, spiking dynamics analysis, ODE neuron model, bifurcation SNN, continuous-time spiking, dynamical systems neuroscienceVotes: 0GitHub stars: 3
- Spiking Neural Networks Fmri Visual DecodingMethodology for using Spiking Neural Network (SNN)-derived visual features as targets for fMRI-based visual semantic decoding, showing superior alignment with brain activity compared to traditional ANN features.Votes: 0GitHub stars: 3
- Spiking Neuron Biological Plausibility Assessment脉冲神经元生物学合理性自动化评估框架，系统化评估人工脉冲神经元与生物神经元的相似度，提供量化指标和可解释分析Votes: 0GitHub stars: 3
- Spiking Oscillation MappingAnalyze and map oscillatory states in balanced spiking neural networks (SNN). Identify regime transitions (silent, asynchronous-irregular, oscillatory) based on synaptic and temporal time scales. Activation: spiking oscillation, SNN regime mapping, balanced network dynamics, oscillatory state analysis.Votes: 0GitHub stars: 3
- Spiking Phase Quantum EncodingSPATE methodology for quantum machine learning — spiking-phase adaptive temporal encoding. Converts real-valued features into leaky integrate-and-fire spike trains and maps spike statistics to quantum rotations, augmented with temporal qubits via controlled phase operations. Use when: (1) designing QML pipelines for temporal data, (2) encoding time-series/tabular data into quantum feature spaces, (3) comparing spike-based vs angle/amplitude encoding quality, (4) building hybrid quantum neural...Votes: 0GitHub stars: 3
- Spiking Quantum EncodingSPATE methodology for spiking-phase adaptive temporal encoding in quantum machine learning. Converts real-valued data into leaky integrate-and-fire spike trains and maps spike statistics to quantum rotations with temporal qubits. Use when: quantum ML encoding, spike-driven temporal encoding, quantum feature preparation, temporal qubits, QML pipeline enhancement.Votes: 0GitHub stars: 3
- Spiking Recurrent Cells Fpga AcceleratorFPGA accelerator for Spiking Recurrent Cell (SRC) neurons — a trade-off between biological plausibility and hardware cost. Removes costly unary operators (tanh, exp) via piecewise approximations, avoids floating-point arithmetic. Achieves 96.31% MNIST accuracy at 0.55-2.2mJ per digit on Artix-7 FPGA. Activation: FPGA spiking neural network, SRC neuron hardware, neuromorphic FPGA, energy-efficient SNN, VHDL SNN implementation, spiking recurrent cells.Votes: 0GitHub stars: 3
- Spiking Reservoir RobustnessRobust spiking reservoir computing framework bridging theory and practice. Introduces robustness interval for tuning reservoirs at edge-of-chaos under experimental uncertainty. Use when working with: (1) Spiking neural networks, (2) Reservoir computing, (3) Neuromorphic computing, (4) Temporal pattern processing. Activation: spiking reservoirs, robustness interval, edge-of-chaos, LIF reservoirs, temporal processing.Votes: 0GitHub stars: 3
- Spiking Rl Neuromorphic Robot ControlSpiking reinforcement learning on neuromorphic hardware for real-time robotic control. Uses fixed random connectivity for temporal structure capture and local e-prop learning rule for efficient online learning. Activation: spiking RL robot control, neuromorphic reinforcement learning, e-prop robot, Loihi robot control, air hockey spiking neural network.Votes: 0GitHub stars: 3
- Spiking Sequence Machines TransformersTheoretical framework showing spiking Sparse Distributed Memory and transformers share identical five functional operations (encoding, context maintenance, retrieval, storage, decoding) with cosine similarity as shared primitive. Formalizes Phase-Latency Isomorphism between sinusoidal positional encoding and spike timing. Activation: spiking transformer, sequence learning theory, phase-latency isomorphism, spike timing positional encoding, SNN transformer equivalence.Votes: 0GitHub stars: 3
- Spiking Temporal Memory Stm Sequence TimingSpiking Temporal Memory (sTM) model for learning sequence timing and control of replay speed in networks of spiking neuronsVotes: 0GitHub stars: 3
- Spiking Tolman Eichenbaum MachineSpiking Tolman-Eichenbaum Machine (sTEM) — biologically realistic spiking neural network implementation of the TEM framework for spatial navigation and memory. Combines grid-place cell dynamics, sequence learning, and hippocampal-entorhinal circuit modeling with spiking neurons. Use when building spiking models of spatial cognition, hippocampal memory systems, grid-place cell interactions, or neuro-inspired navigation in robotics.Votes: 0GitHub stars: 3
- Spiking Transformer Effective DimensionSpiking Transformers Theory - Effective Dimension analysis framework for Spiking Transformers (S-ViT). Provides theoretical bounds on generalization and robustness using VC dimension, Rademacher complexity, and effective dimension metrics. Use when analyzing Spiking Transformer architectures, evaluating SNN generalization bounds, comparing S-ViT with ANN-ViT capacity, or studying temporal coding effects on model complexity. Triggers: spiking transformer, effective dimension, S-ViT, spiking Vi...Votes: 0GitHub stars: 3
- Spiking Transformer UnificationTheoretical framework unifying Spiking Neural Networks (SNNs) and Transformers through shared computational primitives. Based on arXiv:2605.00662 (Bose, 2026). Use when analyzing SNN-Transformer relationships, positional encoding design, sequence learning theory, spike-timing computation, or sparse distributed memory. Activation: spiking transformer, spike-timing attention, phase-latency isomorphism, sparse distributed memory SNN, positional encoding theory, sequence learning theory, SNN tran...Votes: 0GitHub stars: 3
- Spikingbrain2 Foundation ModelsSpikingBrain2.0 - 5B parameter brain-inspired foundation models with efficient long-context and cross-platform inference. Activation: spikingbrain2.0, brain-inspired foundation model, spiking transformer, long-context inference, energy-efficient LLM.Votes: 0GitHub stars: 3
- Spikingbrain2.0 Foundation ModelsSpikingBrain2.0 (SpB2.0) - 5B parameter brain-inspired foundation model with Dual-Space Sparse Attention (DSSA) for efficient long-context and cross-platform inference. Features INT8-Spiking coding for neuromorphic execution and FP8 for GPU acceleration. Activation: SpikingBrain2.0, DSSA, sparse attention, neuromorphic foundation model.Votes: 0GitHub stars: 3
- Spikingjelly Framework脉冲神经网络深度学习框架 SpikingJelly 的使用指南。用于构建、训练和部署 SNN 模型，支持神经形态数据集处理和神经形态芯片部署。触发词：脉冲神经网络、SNN、SpikingJelly、spiking neural network、神经形态计算、neuromorphic computing。Votes: 0GitHub stars: 3
- Spikingmoe Sdprompt Snn**arXiv:2605.23188** | Submitted: 22 May 2026 | cs.NEVotes: 0GitHub stars: 3
- SpikingmoeSpikingMoE — spike-driven Transformer with LGN-inspired Mixture-of-Experts (MoE) for dynamic computation in SNNsVotes: 0GitHub stars: 3
- Spin Wave Superconducting CouplingStrong coupling between propagating spin waves and microwave photons in superconducting resonator-magnetic thin film hybrid circuits. Design methodology for hybrid magnonic quantum systems using YIG-on-substrate integration.Votes: 0GitHub stars: 3
- Spintune Quantum Sensor ReliabilitySpinTune: RL-based optimization of dynamical decoupling pulse sequences for quantum sensor network reliability. Enables adaptive noise-aware DD sequence optimization to mitigate environmental decoherence.Votes: 0GitHub stars: 3
- Split Primes Elekes RonyaiSplit primes and Elekes-Rónyai problem methodology for number theory counterexamples and arithmetic combinatoricsVotes: 0GitHub stars: 3
- Sqdr Cnn Spiking QuantumSQDR-CNN methodology — joint training of convolutional SNNs and quantum circuits with surrogate gradient and quantum data-reupload for parameter-efficient hybrid models.Votes: 0GitHub stars: 3
- Sram Cim Snn AcceleratorSRAM-Based Compute-in-Memory Accelerator for Linear-decay Spiking Neural Networks. Leverages in-memory computing to eliminate the von Neumann bottleneck for SNN inference using linear-decay neuron models compatible with CIM crossbar arrays for ultra-low power edge inference. Activation: SRAM CIM SNN, compute-in-memory spiking network, linear-decay SNN accelerator, CIM crossbar SNN, in-memory computing spiking neural network.Votes: 0GitHub stars: 3
- Srf Similarity Representation FactorizationSimilarity-Based Representation Factorization (SRF) methodology for recovering low-dimensional, non-negative, interpretable embeddings from similarity matricesVotes: 0GitHub stars: 3
- Stambridge Eeg Visual DecodingSTAMBRIDGE: Spectral-Temporal Amplitude-aware Mid-Feature Bridge for EEG Visual Decoding. Two-stage framework combining Spectral-Temporal Amplitude-aware Modulation (STAM) and Mid-Feature Semantic Bridge (MFSB) for zero-shot EEG-to-image retrieval and reconstruction. Achieves 34.50% Top-1 on THINGS-EEG. Activation: EEG visual decoding, EEG-to-image, zero-shot EEG retrieval, spectral-temporal modulation, brain-computer interfaceVotes: 0GitHub stars: 3
- Stars Snn Data Free Knowledge DistillationSTARS (Spike Tail-Aware Relational Synthesis) - plug-and-play method for ANN-to-SNN Data-Free Knowledge Distillation (DFKD). Augments BN-guided synthesis with Relational Consistency Alignment and Tail-Aware Regularization. Achieves up to 4.6% improvement on CIFAR-10 and 6.7% on CIFAR-100. Activation: SNN knowledge distillation, data-free distillation, ANN-to-SNN conversion, tail-aware regularization, relational consistency, spike threshold dynamics, 无数据蒸馏, 跨模态蒸馏.Votes: 0GitHub stars: 3