All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Spiking Neural Network TrainingTraining methodologies for energy-efficient spiking neural networks (SNNs). Covers surrogate gradient methods, spike-timing-dependent plasticity (STDP), and neuromorphic implementation. Activation: SNN, spiking neural network, surrogate gradient, STDP, neuromorphic.Votes: 0GitHub stars: 3
- Spiking Pointnext 3dEnergy-efficient 3D point cloud processing using Spiking Neural Networks. Implements spiking version of PointNeXt architecture for neuromorphic 3D vision systems with comparison to conventional ANN approaches.Votes: 0GitHub stars: 3
- Spiking Polar Trajectory GeneratorSpiking Neural Network (SNN) architecture for generating polar trajectories on neuromorphic hardware, using a winner-take-all (WTA) core with accessory populations that induce controlled transitions in neural activity. Interpretable at the level of system dynamics, energy-efficient, and directly deployable on neuromorphic substrates for size/weight/power-constrained control. Applicable to neuromorphic control, trajectory generation, WTA dynamics, polar-coordinate motor control, robotic naviga...Votes: 0GitHub stars: 3
- Spiking Sequence Generator Polar TrajectoriesSpiking neural network architecture for generating polar trajectories on neuromorphic hardware using winner-take-all dynamics and shunting inhibition. Enables energy-efficient, interpretable motor control with 2-3 orders of magnitude speedup and 3-4 orders of magnitude energy reduction. Activation: spiking sequence generator, polar trajectories, neuromorphic control, WTA architecture, SpiNNaker2, motor control, shunting inhibitionVotes: 0GitHub stars: 3
- Spiking Sleep Waves Memory ConsolidationSpiking neural network modeling of sleep-related brain waves (spindles, slow oscillations, theta-gamma coupling) for understanding memory consolidation mechanisms. Applies to brain simulation, sleep disorder modeling, neuromorphic memory systems, cognitive AI. 触发词: sleep brain waves, spindles, slow oscillations, theta-gamma coupling, spiking sleep model, memory consolidation SNN, thalamocortical, hippocampalVotes: 0GitHub stars: 3
- Spiking Transformer Effective Dimension TheorySpiking Transformers: Effective Dimension Theory — arXiv:2604.15769 (April 2026). Develops effective dimension theory for Spiking Transformers via Neural Tangent Kernel (NTK) framework, analyzing how spiking mechanisms (threshold, reset, refractory period) reduce model expressivity and enable compression. Covers firing rate statistics, membrane time constants, optimal hyperparameter derivation, and spiking NTK formulation.Votes: 0GitHub stars: 3
- Spiking Transformer Energy EfficiencyEnergy-efficient Spiking Transformer methodology using attention-driven spike generation, spike-driven self-attention, and surrogate gradient training. Achieves 3-5x energy reduction vs conventional Transformers. Use for: neuromorphic vision, efficient Transformers, event-based processing, SNN-Transformer hybrid. Trigger: 脉冲Transformer、spiking transformer、SNN、energy-efficient、attentionVotes: 0GitHub stars: 3
- Spiking Transformer GemstSkill for spiking transformer gemstVotes: 0GitHub stars: 3
- Spikingmoe Sdprompt SnnResearch skill for SDPrompt-guided dynamic expert fusion in spiking neural networks.Votes: 0GitHub stars: 3
- Spikingmot Spike Driven Multi Object TrackerSpikingMOT: A Spike-Driven Multi-Object Tracker that uses brain-inspired spiking neural networks for efficient trajectory prediction and target association. Achieves state-of-the-art performance while reducing parameters by 72% and energy by 86.7%. Use when working with multi-object tracking, spiking neural networks, or efficient computer vision applications.Votes: 0GitHub stars: 3
- Spikingnav Embodied Navigation SnnSpikingNav methodology for robust embodied navigation using Spiking Neural Networks (SNNs). Combines Spiking Sensing Encoder (SSE) and Spiking Policy Network (SPN) for energy-efficient, corruption-resistant navigation in resource-constrained environments. Use when working with embodied AI agents, neuromorphic hardware, or SNN-based robotics navigation systems.Votes: 0GitHub stars: 3
- Spinnaker2 Neuromorphic Hardware PlatformSpiNNaker2 chip: a many-core platform for flexible and scalable brain-inspired computing that bridges deep learning and neuromorphic computing. Use when working with neuromorphic hardware design, spiking neural network acceleration, or brain-inspired computing platforms.Votes: 0GitHub stars: 3
- Statrack Spiking Uav TrackingSTATrack fully spiking UAV tracker using adaptive mutual information maximization — neuromorphic event-driven UAV tracking with SNN architecture. Activation: UAV tracking, spiking neural network, event camera, neuromorphic, mutual information, object tracking, drone, autonomous.Votes: 0GitHub stars: 3
- Stochastic Spiking Attention Accelerating Attention With Stochastic Computing In Spiking Networks**arXiv ID:** 2402.09109 **Authors:** Zihang Song, Prabodh Katti, Osvaldo Simeone, Bipin Rajendran **Published:** 2024-02-14T11:47:19Z **Abstract:** Spiking Neural Networks (SNNs) have been recently integrated into Transformer architectures due to their potential to reduce computational demands and to improve power efficiency. Yet, the implementation of the attention mechanism using spiking signals on general-purpose computing platforms remains inefficient. In this paper, we propose a novel f...Votes: 0GitHub stars: 3
- Submw Neuromorphic Snn Audio Processing Applications With Rockpool And Xylo**arXiv ID:** 2208.12991 **Authors:** Hannah Bos, Dylan Muir **Published:** 2022-08-27T11:50:32Z **Abstract:** Spiking Neural Networks (SNNs) provide an efficient computational mechanism for temporal signal processing, especially when coupled with low-power SNN inference ASICs. SNNs have been historically difficult to configure, lacking a general method for finding solutions for arbitrary tasks. In recent years, gradient-descent optimization methods have been applied to SNNs with increasing e...Votes: 0GitHub stars: 3
- Superneuromat Efficient Matrix Snn SimulatorSuperNeuroMAT: Matrix-based SNN simulator.Votes: 0GitHub stars: 3
- Tecos Lvm Spiking ModelSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Temporal Poisoning Clean Label Backdoors SnnSkill for understanding and applying clean-label backdoor attacks via event redistribution in Spiking Neural Networks (SNNs) from arXiv paper 2607.28075Votes: 0GitHub stars: 3
- Temporal Switch Neuromorphic TransferModel-free temporal-switch (TS) framework for transferable lightweight neuromorphic computing. Enables direct transfer of trained models to unseen hardware devices without post-training calibration by incorporating a broader spectrum of devices during training. Addresses device-to-device variations that undermine practical advantages of neuromorphic computing. Activation: temporal switch framework, neuromorphic transfer, device variation robustness, memristor reservoir computing, model-free t...Votes: 0GitHub stars: 3
- The Enduring Dominance Of Deep Neural Networks A Critical Analysis Of The Fundamental Limitations Of Quantum Machine Learning And Spiking Neural Networks**arXiv ID:** 2510.08591 **Authors:** Takehiro Ishikawa **Published:** 2025-10-04T11:00:46Z **Abstract:** Recent advancements in QML and SNNs have generated considerable excitement, promising exponential speedups and brain-like energy efficiency to revolutionize AI. However, this paper argues that they are unlikely to displace DNNs in the near term. QML struggles with adapting backpropagation due to unitary constraints, measurement-induced state collapse, barren plateaus, and high measurement...Votes: 0GitHub stars: 3
- Threefactor Learning In Spiking Neural Networks An Overview Of Methods And Trends From A Machine Learning Perspective**arXiv ID:** 2504.05341 **Authors:** Szymon Mazurek, Jakub Caputa, Jan K. Argasiński, Maciej Wielgosz **Published:** 2025-04-06T08:10:16Z **Abstract:** Three-factor learning rules in Spiking Neural Networks (SNNs) have emerged as a crucial extension to traditional Hebbian learning and Spike-Timing-Dependent Plasticity (STDP), incorporating neuromodulatory signals to improve adaptation and learning efficiency. These mechanisms enhance biological plausibility and facilitate improved credit ass...Votes: 0GitHub stars: 3
- Threshold Based Snn Event Driven Status Update SystemsThreshold policies for event-driven IoT status updates.Votes: 0GitHub stars: 3
- Threshold Based Snn Event Driven Status UpdateThreshold-Based Spiking Neural Networks for Event-Driven Status Update Systems - lightweight RL approach using SNNs with explicit threshold policy representation for IoT status updates that jointly minimizes Age of Information (AoI) and transmission energy. Use when designing energy-efficient event-driven IoT systems, optimizing information freshness vs energy trade-offs, or implementing threshold policies with SNNs.Votes: 0GitHub stars: 3
- Threshold Based Snn Event Driven StatusThreshold-Based Spiking Neural Networks for Event-Driven Status Update Systems - lightweight RL approach using SNNs with explicit threshold policy representation for IoT energy-efficient communication. Use when optimizing Age of Information (AoI) and transmission energy in event-driven IoT systems.Votes: 0GitHub stars: 3
- Threshold Based Snn Event DrivenSNN threshold policies for event-driven IoT status updates.Votes: 0GitHub stars: 3
- Training Probabilistic Spiking Neural Networks With Firsttospike Decoding**arXiv ID:** 1710.10704 **Authors:** Alireza Bagheri, Osvaldo Simeone, Bipin Rajendran **Published:** 2017-10-29T22:13:53Z **Abstract:** Third-generation neural networks, or Spiking Neural Networks (SNNs), aim at harnessing the energy efficiency of spike-domain processing by building on computing elements that operate on, and exchange, spikes. In this paper, the problem of training a two-layer SNN is studied for the purpose of classification, under a Generalized Linear Model (GLM) probabilis...Votes: 0GitHub stars: 3
- Training Spiking Neural Networks Via Augmented Direct Feedback Alignment**arXiv ID:** 2409.07776 **Authors:** Yongbo Zhang, Katsuma Inoue, Mitsumasa Nakajima, Toshikazu Hashimoto, Yasuo Kuniyoshi, Kohei Nakajima **Published:** 2024-09-12T06:22:44Z **Abstract:** Spiking neural networks (SNNs), the models inspired by the mechanisms of real neurons in the brain, transmit and represent information by employing discrete action potentials or spikes. The sparse, asynchronous properties of information processing make SNNs highly energy efficient, leading to SNNs being pr...Votes: 0GitHub stars: 3
- Transport Mean Field Snn DynamicsTransport mean field methodology for approximating macroscopic dynamics of spiking neural networks. Analytically derives firing rate fluctuations in coupled integrate-and-fire populations via solutions to the transport equation and Fokker-Planck system.Votes: 0GitHub stars: 3
- Transport Mean Field SnnTransport Mean Field methodology for approximate macroscopic dynamics of spiking neural networks. Derives population firing rate evolution from initial voltage distributions via transport (advection) solution to the Fokker-Planck system, unlike earlier mean field approaches based on asynchronous steady-state solutions. Assumes slow time-varying inputs and excitation-driven regime. Use when: analyzing SNN population dynamics, deriving mean field approximations, studying firing rate fluctuation...Votes: 0GitHub stars: 3
- Uncertainty Token Pruning SpikingTraining-free token pruning for spiking transformers using temporal uncertainty patterns. Models token-wise class evidence with Dirichlet distribution and summarizes each token's temporal uncertainty via mean and fluctuation across spiking steps. Tokens with low uncertainty contribution are pruned during inference. Use when optimizing spiking transformer inference efficiency, reducing token redundancy in SNN vision models, or implementing plug-and-play token reduction for neuromorphic models....Votes: 0GitHub stars: 3
- Unsupervised Anomaly Detection In Stream Data With Online Evolving Spiking Neural Networks**arXiv ID:** 1912.08785 **Authors:** Piotr S. Maciąg, Marzena Kryszkiewicz, Robert Bembenik, Jesus L. Lobo, Javier Del Ser **Published:** 2019-12-18T18:36:01Z **Abstract:** Unsupervised anomaly discovery in stream data is a research topic with many practical applications. However, in many cases, it is not easy to collect enough training data with labeled anomalies for supervised learning of an anomaly detector in order to deploy it later for identification of real anomalies in streaming data...Votes: 0GitHub stars: 3
- Ven Circuit Snn Social LearningVENCircuit methodology — Von Economo neurons (VENs) as acquisition scaffolds in recurrent spiking neural networks. Combines computational modeling with clinical predictions for bvFTD and autism. Use when: studying VENs, social learning in SNNs, gradient pathway analysis, clinical prediction from computational models, developmental scaffolding in neural networks.Votes: 0GitHub stars: 3
- Vo2 Mott Oscillator Spiking Neuron基于VO2 Mott振荡器的单片集成脉冲神经元，采用BEOL工艺在CMOS兼容SOI平台上实现1T-1MR架构，具备栅极可调振荡、超低能耗和纳米级耦合特性Votes: 0GitHub stars: 3
- Vo2 Mott Spiking Neuron HardwareVO2 Mott oscillator-based spiking neuron hardware for neuromorphic computing. Monolithic CMOS-BEOL integration of energy-efficient spiking neurons using vanadium dioxide phase-transition materials. Activation: vo2, mott, spiking neuron, neuromorphic hardware, phase-transition, BEOL integration.Votes: 0GitHub stars: 3
- Vor Spiking Cerebellar RobotSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Vs Gno Variable Spiking Graph Neural OperatorVariable Spiking Graph Neural Operator (VS-GNO) for edge-deployable virtual sensing on irregular geometries. Integrates spectral-spatial graph convolution with Variable Spiking Neuron (VSN) and energy-error balance loss for sparse-to-dense reconstruction with controllable spiking sparsity. Achieves 0.71% error at 15% spiking on complex engineering geometries.Votes: 0GitHub stars: 3
- Wavesense Efficient Temporal Convolutions With Spiking Neural Networks For Keyword Spotting**arXiv ID:** 2111.01456 **Authors:** Philipp Weidel, Sadique Sheik **Published:** 2021-11-02T09:38:22Z **Abstract:** Ultra-low power local signal processing is a crucial aspect for edge applications on always-on devices. Neuromorphic processors emulating spiking neural networks show great computational power while fulfilling the limited power budget as needed in this domain. In this work we propose spiking neural dynamics as a natural alternative to dilated temporal convolutions. We extend t...Votes: 0GitHub stars: 3
- Working Memory Recurrent Spiking Neural NetworksWorking memory implementation in recurrent Spiking Neural Networks using heterogeneous synaptic delays (D=41) and surrogate gradient BPTT, achieving perfect F1 on pattern storage and recall tasks.Votes: 0GitHub stars: 3
- Working Memory Recurrent Spiking NeuralWorking memory -- the ability to store and recall precise temporal patterns of neural activity -- remains an open challenge for spiking neural networks (SNNs). We propose a recurre...Votes: 0GitHub stars: 3
- Yana Neuromorphic SimulationGPU-accelerated neuromorphic simulation methodology with thousands of neurons on a single GPU. Enables large-scale spiking neural network simulation for connectomic-scale neural circuits. Trigger words: yana, neuromorphic simulation, gpu-accelerated snn, large-scale spiking simulation, connectomic simulation, thousands neurons gpu, spiking neural network scaling.Votes: 0GitHub stars: 3
- Spikingmot Spike Driven Multi Object TrackerSpikingMOT framework for spike-driven multi-object tracking using spiking neural networks. Implements activation sparsity preference (ASP) with adaptive sparse trajectory dynamics modeling, achieving state-of-the-art performance while reducing parameters by 72% and energy by 86.7%. Use when implementing efficient multi-object tracking, spiking neural network applications, or sparse trajectory prediction in computer vision.Votes: 0GitHub stars: 3
- Stst Jepa Eeg FoundationSTST-JEPA: Shallow-Target Spatio-Temporal Joint Embedding Prediction Architecture for EEG self-supervised learning. Combines latent-prediction objective with auxiliary signal-reconstruction term under spatiotemporal block masks. Pretrained on 47,703 EEG sessions (ages 5-81), achieves MAE=3.06 years for brain-age regression. Native 30-second windows achieve rank-1 on NeuralBench x EEGD leaderboard for sex classification (BA=0.911) and age prediction (r=0.749). Age-prediction residual negativel...Votes: 0GitHub stars: 3
- Subjective Functions 251215948A skill for modeling subjective experiences as emergent properties of neural processes based on the mathematical framework of subjective functions. Use this skill when you need to bridge objective neural measurements with subjective reports, model endogenous objective functions, or study consciousness in biological and artificial systems.Votes: 0GitHub stars: 3
- Arbitrary Photon Waveform ControlArbitrary temporal waveform control of single photons during spontaneous emission. Methodology for shaping photon wavepackets to optimize quantum state transfer in hybrid quantum systems. Applicable to quantum networking, atom-photon interfaces, and quantum memory protocols.Votes: 0GitHub stars: 3
- Qnd Measurements Fault Tolerant Biased NoiseQuantum non-demolition (QND) multi-qubit Pauli measurements as a practical primitive for fault-tolerant quantum computation against biased noise. Replaces bias-preserving CNOT gates with QND ZZ measurements, enabling 6× qubit overhead reduction. arXiv: 2605.24262Votes: 0GitHub stars: 3
- Thermodynamics Quantum Reservoir ComputingNon-equilibrium thermodynamic framework for quantum reservoir computing that links predictive performance to energetic costs. Establishes fundamental limits and trade-offs in quantum neuromorphic hardware.Votes: 0GitHub stars: 3
- Threshold Based Snn Event Driven Status UpdateThreshold-Based Spiking Neural Networks for Event-Driven Status Update Systems - lightweight RL approach using SNNs with explicit threshold policy representation for IoT status updates that jointly minimizes Age of Information (AoI) and transmission energy. Use when designing energy-efficient event-driven IoT systems, optimizing information freshness vs energy trade-offs, or implementing threshold policies with SNNs.Votes: 0GitHub stars: 3
- Repository Migration WorkflowSystematic workflow for repository reorganization when structure limits are hit (GitHub 1000-entry truncation, directory bloat). Covers problem identification, domain-based classification, git history preservation, and migration execution. Use when: (1) GitHub shows truncation warning in directory listings, (2) Flat directory exceeds organizational limits, (3) Need to restructure repository while preserving git history, (4) Moving large numbers of files/directories in a repo. Activation: repo...Votes: 0GitHub stars: 3
- Research Api Fallback StrategyFallback strategies for automated research when external APIs fail. Use when: (1) arXiv/semantic scholar APIs return errors, (2) scheduled research jobs encounter connectivity issues, (3) need to pivot from live search to knowledge-based skill creation, (4) automated research pipelines need resilience against external service failures.Votes: 0GitHub stars: 3
- Research Skill ExtractorMeta-skill that extracts reusable skill patterns from research papers (arxiv), scientific workflows, and knowledge graph analysis. Activates when analyzing papers for skill patterns, creating skills from research methodologies, or mining patterns from scientific literature. Keywords: extract skill from paper, research skill mining, 论文技能提炼, paper to skill, arxiv skill extractor.Votes: 0GitHub stars: 3