All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Slicer Robotms Neuro NavigationOpen-source 3D Slicer extension for robot-assisted transcranial magnetic stimulation (Robo-TMS). Enables accurate, reproducible non-invasive brain stimulation with image-guided robotic intervention. Activation: robot TMS, Robo-TMS, Slicer extension, TMS navigation, transcranial magnetic stimulation robot, neurostimulation robotic.Votes: 0GitHub stars: 3
- Slow Rhythms Delay Coupled OscillatorsSystematic bifurcation analysis framework for discovering delay-induced slow rhythms in neural oscillator networks. Phase reduction + numerical continuation reveals Hopf/heteroclinic/saddle-node bifurcations organizing slow-fast dynamics. Applicable to FHN, ML, QIF models. Activation: delay-induced rhythms, slow-fast dynamics, phase reduction, bifurcation analysis, neural oscillators, numerical continuation.Votes: 0GitHub stars: 3
- Smartvector Neuroscience Embeddings RagSelf-aware vector embeddings for RAG with neuroscience-inspired temporal weighting, confidence scoring, and relational knowledge. SmartVector framework addressing version drift and temporal inconsistency in retrieval systems. Keywords: SmartVector, self-aware embeddings, RAG, temporal knowledge, vector embeddings, neuroscience, retrieval-augmented generation.Votes: 0GitHub stars: 3
- Smartvector Neuroscience RagSmartVector: Self-aware vector embeddings for RAG with temporal awareness, confidence decay, and relational awareness. Neuroscience-inspired hippocampal-neocortical consolidation. Activation triggers: vector embeddings, temporal knowledge, confidence decay, relational embeddings, memory consolidation, versioned RAG, smart vectors.Votes: 0GitHub stars: 3
- Snn Astrocyte LearningSpiking Neural Networks with Astrocyte-Like Units - incorporating glial cell dynamics for improved learning, achieving optimal performance at 2:1 astrocyte-to-neuron ratio matching biological estimates. Activation triggers: astrocyte, glial cells, tripartite synapse, SNN learning, liquid state machine, biological realism.Votes: 0GitHub stars: 3
- Snn Edge Intelligence SurveyBrain-inspired AI for Edge Intelligence: a systematic review - Systematic analysis of SNN deployment paradox in edge comput. Activation triggers: snn, edge, intelligence, neuroscience, SNN.Votes: 0GitHub stars: 3
- Snn Fairness Benchmark HardwareFirst systematic fairness benchmark for Spiking Neural Networks (SNNs) addressing three dimensions of realism: data bias, spurious feature leakage, and hardware effects. Evaluates fairness-performance trade-offs under resource constraints using four cross-demographic datasets with controlled bias injections and neuromorphic hardware simulators. Activation: SNN fairness, spiking neural network bias, neuromorphic fairness, hardware fairness, edge deployment fairness, fairness benchmark, SNN ben...Votes: 0GitHub stars: 3
- Snn Firing Distribution QuantizationEarth Mover's Distance (EMD) methodology for evaluating SNN quantization beyond accuracy. Diagnoses firing distribution divergence caused by weight and membrane quantization. Activation: SNN quantization, firing distribution, EMD metric, membrane quantization, SEW-ResNet, deployment evaluation, spiking network quantization quality.Votes: 0GitHub stars: 3
- Snn Fmri Visual DecodingSpiking Neural Networks for fMRI-Based Visual Semantic Decoding - methodology for using SNN-derived visual features as alternative targets for fMRI-based visual decoding, demonstrating stronger alignment with fMRI responses and improved visual semantic decoding performance compared to ANN-derived features.Votes: 0GitHub stars: 3
- Snn Fpga Hardware Software CodesignHardware-software co-design framework for event-driven SNN deployment on low-cost neuromorphic FPGAs. Unifies hardware and algorithm design with automated optimization. Keywords: SNN FPGA, hardware-software co-design, neuromorphic deployment, event-driven, low-cost FPGA.Votes: 0GitHub stars: 3
- Snn Internal Noise AnalysisComprehensive analysis of internal noise mechanisms in spiking neural networks, identifying membrane potential noise as most detrimental and proposing input pre-filtering strategies for robustness. Activation triggers: internal noise, spiking neural network, noise analysis, snn robustness, membrane potential noise, additive noise, multiplicative noise.Votes: 0GitHub stars: 3
- Snn Learning Survey脉冲神经网络学习规则综合分析技能。涵盖无监督（STDP及变体）、监督（代理梯度）、强化学习及混合学习范式。提供SNN训练方法选择指南、关键参数配置和性能比较。适用于脉冲神经网络、神经形态计算、低功耗AI、事件驱动系统。触发词：SNN learning rules, STDP, surrogate gradient, neuromorphic computing, spiking neural network training, 脉冲神经网络学习Votes: 0GitHub stars: 3
- Snn Low Level Vision[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]Votes: 0GitHub stars: 3
- Snn Mcu Fullfeature EdgeFull-feature Spiking Neural Network simulation on microcontrollers for edge neuromorphic applications. Enables ultra-low power SNN deployment on resource-constrained devices. Triggers: SNN, microcontroller, edge computing, neuromorphic, MCU.Votes: 0GitHub stars: 3
- Snn Microcontroller SimulationFull-feature Spiking Neural Network simulation on microcontrollers (RP2350) using IEEE 16-bit floating point. Demonstrates Synfire4 benchmark (1200 neurons) at 97.5% accuracy with 20mW power consumption. Enables neuromorphic edge computing with 5x better energy efficiency than ARM Cortex-A53. Triggers: SNN microcontroller, CARLsim MCU, 16-bit SNN, neuromorphic edgeVotes: 0GitHub stars: 3
- Snn Mlir Neuromorphic CompilationSNN-MLIR编译方法论 — MLIR方言用于将神经形态SNN从NIR编译到裸机C代码。支持浮点和量化数据，自动重缩放操作，生成依赖-free C11代码。Votes: 0GitHub stars: 3
- Snn Near Sensor Noise Filter DvsSNN-based near-sensor noise filter (SNNF) for Dynamic Vision Sensors (DVS) using Event-Based Binary Image (EBBI) representation. Eliminates Background Activity noise with spike-based computation. Use when: event camera noise filtering, neuromorphic vision, DVS preprocessing, IoVT edge applications, SNN hardware deployment, or near-sensor filtering.Votes: 0GitHub stars: 3
- Snn Performance AnalysisComprehensive performance analysis of Spiking Neural Networks (SNNs) comparing neuron models, training strategies, and performance metrics. Use when evaluating SNN architectures, choosing training methods (surrogate gradient, ANN-to-SNN conversion, STDP), analyzing energy consumption vs. accuracy trade-offs, or optimizing SNNs for robotics, neuromorphic vision, and edge AI applications.Votes: 0GitHub stars: 3
- Snn Quantized Dynamics IntegerInteger-state dynamics of quantized spiking neural networks for efficient hardware deployment. Analyzes how quantization affects SNN dynamics, revealing that integer-state SNNs exhibit distinct dynamical regimes. Provides framework for designing hardware-efficient SNNs with guaranteed dynamical properties. Use for SNN quantization, neuromorphic hardware deployment, low-precision SNN design. Activation: quantized SNN, integer SNN, hardware-efficient SNN, low-precision spiking, SNN quantization...Votes: 0GitHub stars: 3
- Snn Rademacher Generalization BoundsTheoretical generalization bounds for Spiking Neural Networks using Rademacher complexity analysis. Characterizes how SNN configuration affects generalization performance. Activation: SNN generalization, Rademacher complexity, spiking network theory, generalization bound, theoretical SNN analysis, excitation-dependent bound.Votes: 0GitHub stars: 3
- Snn Sequence Timing Replay V2Spiking Temporal Memory (sTM) model extension for learning sequence timing and controlling replay speed via oscillatory background inputsVotes: 0GitHub stars: 3
- Snn Sequence Timing ReplayBiologically plausible spiking neural network model for learning sequence timing and controlling replay speed. Extends the spiking Temporal Memory (sTM) model with element-specific duration encoding via sequential activation of neuronal populations, and uses oscillatory background inputs as a clock signal for flexible speed control. Use when working with: spiking neural networks for sequence learning, temporal memory models, sequence replay in SNNs, timing encoding in neural populations, osci...Votes: 0GitHub stars: 3
- Snn Universal Approximation TheoryRigorous mathematical analysis establishing universal approximation theorem for Spiking Neural Networks with LIF neurons, proving SNNs can approximate continuous functions to arbitrary accuracy. Analyzes spike timing dynamics and stability conditions across layers.Votes: 0GitHub stars: 3
- Snn Universal ApproximationUniversal approximation theorem for Spiking Neural Networks (SNNs) with LIF neurons. Use when proving SNN expressiveness, analyzing spike timing encoding, understanding theoretical foundations of SNN approximation power, or studying spike count dynamics across network layers. Provides mathematical framework for SNN function approximation and dynamical constraints.Votes: 0GitHub stars: 3
- Snn Working Memory DelaysWorking memory implementation in recurrent spiking neural networks with heterogeneous delays. Uses diverse synaptic delay distributions to create multiple timescales, enabling storage and recall of precise temporal patterns in SNNs. Solves the temporal credit assignment problem in spiking networks. Activation: SNN working memory, spiking neural network memory, heterogeneous delays, temporal pattern storage, recurrent SNN, 脉冲神经网络工作记忆, 异质延迟Votes: 0GitHub stars: 3
- Snn Working Memory Heterogeneous Delays V2Working memory implementation in recurrent spiking neural networks with heterogeneous synaptic delays. Models synapses with multiple delays as weight tensors, trained with surrogate-gradient backpropagation through time. Enables precise temporal pattern storage and recall for energy-efficient neuromorphic edge deployment. Activation: working memory SNN, spiking neural network memory, heterogeneous delays, temporal pattern storage, recurrent SNN.Votes: 0GitHub stars: 3
- Snn Working Memory Heterogeneous Delays V3Working memory implementation in recurrent spiking neural networks using heterogeneous synaptic delays. Uses multi-delay synapse weight tensors to store temporal patterns. Activation: snn, working-memory, spiking, delays, temporal-patterns, neuroscience, brain, neuralVotes: 0GitHub stars: 3
- Snn Working Memory Heterogeneous DelaysWorking memory implementation in recurrent spiking neural networks using heterogeneous synaptic delays. Leverages diverse axonal conduction delays to create temporally distributed representations, enabling persistent activity without continuous stimulation. Use for SNN-based working memory, temporal sequence processing, and delay-dependent neural computation. Activation: working memory SNN, heterogeneous delays, synaptic delay, recurrent SNN memory, temporal representation, delay-based memoryVotes: 0GitHub stars: 3
- Snn4agents A Framework For Developing Energyefficient Embodied Spiking Neural Networks For Autonomous Agents**arXiv ID:** 2404.09331 **Authors:** Rachmad Vidya Wicaksana Putra, Alberto Marchisio, Muhammad Shafique **Published:** 2024-04-14T19:06:00Z **Abstract:** Recent trends have shown that autonomous agents, such as Autonomous Ground Vehicles (AGVs), Unmanned Aerial Vehicles (UAVs), and mobile robots, effectively improve human productivity in solving diverse tasks. However, since these agents are typically powered by portable batteries, they require extremely low power/energy consumption to oper...Votes: 0GitHub stars: 3
- Snnf Near Sensor Dvs Noise FilterSNNF: SNN-based Near-Sensor Noise Filter for Dynamic Vision Sensors. Hardware-efficient BA noise filtering using compact EBBI representation, parallel memory architecture, and single-layer SNN classifier. Achieves AUC 0.89 with ~11% memory and ~40% logic of state-of-the-art filters. Ideal for resource-constrained edge DVS applications. Activation: SNNF, DVS noise filter, event-based binary image, background activity noise, near-sensor computing, dynamic vision sensor, EBBI, spatiotemporal fil...Votes: 0GitHub stars: 3
- Social Exclusion Brain Dynamics社会排斥中的全局脑动力学分析方法。使用功能连接预测社会行为一致性，结合心智化网络和社会疼痛网络分析。触发词：社会排斥、social exclusion、脑动力学、社会行为预测、心智化网络、mentalizing network、社会疼痛。Votes: 0GitHub stars: 3
- Socratic Swe Self Evolving Coding AgentsSelf-Evolving Coding Agents via Trace-Derived Agent Skills (Socratic-SWE). Closed-loop framework that reuses solving traces to distill agent skills, generate targeted repair tasks, and iteratively improve Solver performance. Achieves 50.40% on SWE-bench Verified. Activation: self-evolving agent, coding agent training, trace-derived skills, SWE bench, agent skill distillation.Votes: 0GitHub stars: 3
- Soliton Waves Wstdp SnnSoliton-like wave propagation in 2D recurrent SNNs with weighted STDP - minimal biologically plausible spiking model combining multiplicative STDP, divisive normalization, homeostatic threshold adaptation, and refractory period to produce self-propagating dissipative soliton waves, wave collision encoding, and spatial memory from local plasticity aloneVotes: 0GitHub stars: 3
- Solving The Spike Feature Information Vanishing Problem In Spiking Deep Q Network With Potential Based Normalization**arXiv ID:** 2206.03654 **Authors:** Yinqian Sun, Yi Zeng, Yang Li **Published:** 2022-06-08T02:45:18Z **Abstract:** Brain inspired spiking neural networks (SNNs) have been successfully applied to many pattern recognition domains. The SNNs based deep structure have achieved considerable results in perceptual tasks, such as image classification, target detection. However, the application of deep SNNs in reinforcement learning (RL) tasks is still a problem to be explored. Although there have b...Votes: 0GitHub stars: 3
- Sparse Autoencoder Brain Llm TopographySparse Autoencoders (SAEs) from mechanistic interpretability bridge LLM internal representations with cortical semantic topography in human brains. Decomposes LLMs (GPT-2 XL, Llama-3.1-8B) into 16K-32K interpretable features per layer; semantic features recover 94% of brain encoding performance. Five a priori semantic subcategories map onto distinct brain regions via formal convergence testing. Validated across English, Chinese, French. Accepted at CoNLL 2026. Activation: sparse autoencoder, ...Votes: 0GitHub stars: 3
- Sparse Mamba Decoder QecSparse Mamba Decoder (SMD) for quantum error correction — a defect-centric neural decoder using Mamba state-space model that processes only active detection events (k ≪ d²R) achieving O(k) complexity on surface codes. 95-467x faster than Tesseract near-MLD decoder.Votes: 0GitHub stars: 3
- Sparse Mamba Qec DecoderSparse Mamba Decoder (SMD) for quantum error correction — defect-centric neural decoder using state-space (Mamba) backbone. Processes only k active detection events (O(k) complexity) instead of full O(d²R) syndrome array. Reduces MWPM logical error rate by up to 49%, runs 95-467x faster than Tesseract near-MLD, achieves 24-57μs latency across d=3-9. Activation: sparse mamba decoder, SMD, QEC neural decoder, surface code Mamba, defect-centric decoding, sparse syndrome processing, quantum error...Votes: 0GitHub stars: 3
- Sparse Neural Connectivity RecoveryCovariance-based method with Granger-causality refinement for recovering sparse neural connectivity from partial measurements.Votes: 0GitHub stars: 3
- Sparse Temporal Context ReconfigurationJoint sparse coding and temporal dynamics methodology for context reconfiguration in lifelong learning. Identifies how sparsity and temporal structure in neural populations enable stable adaptation without catastrophic forgetting. Applies to SNN design, continual learning, and computational neuroscience.Votes: 0GitHub stars: 3
- Sparsity Neuromorphic Impulse RadioSparsity-aware event-driven impulse radio transceivers for reliable wireless neuromorphic inference. Activation: neuromorphic wireless, sparsity-aware radio, event-driven impulse, spike transmission.Votes: 0GitHub stars: 3
- Spatiotemporal Tdann Mt Direction MapsSpatiotemporal TDANN framework for modeling the emergence of direction-selective maps in primate MT cortex via self-supervised contrastive optimization with spatial regularization. Unifies ventral and dorsal stream topographic self-organization. arXiv: 2605.11718 (May 2026).Votes: 0GitHub stars: 3
- Spatiotemporal TdannSpatiotemporal Topographic Deep Artificial Neural Network (TDANN) methodology for modeling dorsal stream cortical self-organization. Extends TDANN to motion-sensitive MT area using 3D ResNet trained with MoCo self-supervised contrastive learning on naturalistic videos plus biologically inspired spatial loss. Spontaneously emerges brain-like direction maps and pinwheel structures. Use when: modeling visual cortex topography, self-organized cortical maps, spatiotemporal neural representations, ...Votes: 0GitHub stars: 3
- Spectralot Brain AlignmentFast Whole-Brain, Geometry-Aware Functional Alignment for Cross-Subject Decoding using Spectral Optimal Transport (SpectralOT) method for fMRI data analysisVotes: 0GitHub stars: 3
- Spider Directed Connectivity StitchingSPIDER: Non-parametric frequency-domain framework for recovering directed brain connectivity from incomplete asynchronous recordings. Stitches power-spectra across sessions. Activation: effective connectivity, directed information flow, SPIDER, brain connectivity stitching, 脑连接拼接, 有效连接Votes: 0GitHub stars: 3
- Spider Directed ConnectivitySPIDER: non-parametric frequency-domain framework for inferring directed effective connectivity from incomplete, asynchronous recordings via stitched power-spectra and spectral factorization.Votes: 0GitHub stars: 3
- Spike Agreement Dependent PlasticitySpike Agreement Dependent Plasticity (SADP) - biologically inspired learning rule for SNNs using population-level correlation metrics instead of precise spike timing. Activation triggers: spike agreement, synaptic plasticity, SNN learning, bio-inspired learning, population correlation, neuromorphic learning.Votes: 0GitHub stars: 3
- Spike Forecast Behavioral DecodingImplicit behavioral decoding from next-step spike forecasts at population scale. Methodology from paper 'Implicit Behavioral Decoding from Next-Step Spike Forecasts at Population Scale' (arXiv: 2605.12999). Demonstrates that a single Mamba forecaster, trained only on next-step spike counts at Neuropixels scale, implicitly learns behavioral representations without behavioral labels. Use when: building closed-loop BCIs, neural population forecasting, spike train prediction, behavioral decoding ...Votes: 0GitHub stars: 3
- Spike Forecast BehavioralImplicit behavioral decoding from next-step spike forecasts at population scale. Joint learning of neural population forecasting and behavioral readout from spiking activity. Use when: closed-loop BCI systems, neural population modeling, behavioral decoding from neural activity, spike-based prediction, population-scale neural forecasting.Votes: 0GitHub stars: 3
- Spike Image Decoder从神经脉冲重建视觉场景的深度学习框架（SID）。端到端解码器， 从视网膜神经节细胞脉冲重建静态图像和动态视频。 触发词：神经解码、视觉重建、脉冲解码、脑机接口、神经假体、 neural decoding, visual reconstruction, spike decoding, brain-machine interface。Votes: 0GitHub stars: 3
- Spike Mllm Multimodal SpikingSpikeMLLM - Spike-based Multimodal Large Language Models via Modality-Specific Temporal Scales (MSTS) and Temporally Compressed LIF (TC-LIF). Enables energy-efficient multimodal AI with 9.06x throughput and 25.8x power efficiency via algorithm-hardware co-design. Triggers: spike MLLM, multimodal SNN, temporal compression, neuromorphic multimodalVotes: 0GitHub stars: 3