All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Cognisnn Random Graph ArchitectureCogniSNN: Enabling Neuron-Expandability, Pathway-Reusability, and Dynamic-Configurability with Random Graph Architectures in Spiking Neural NetworksVotes: 0GitHub stars: 3
- Cognisnn Random GraphCogniSNN - Cognition-aware Spiking Neural Networks with Random Graph Architecture. Brain-inspired SNN with neuron-expandability, pathway-reusability, and dynamic-configurability. Use when implementing energy-efficient SNNs, neuromorphic computing, continual learning in SNNs, or brain-inspired neural architectures. Activation: CogniSNN, spiking neural network, SNN, random graph, brain-inspired, neuromorphic, continual learning, energy-efficient neural network, spike-based learning.Votes: 0GitHub stars: 3
- Collapse Or Preserve Datadependent Temporal Aggregation For Spiking Neural Network Acceleration**arXiv ID:** 2603.13810 **Authors:** Jiahao Qin **Published:** 2026-03-14T07:30:22Z **Abstract:** Spike sparsity is widely believed to enable efficient spiking neural network (SNN) inference on GPU hardware. We demonstrate this is an illusion: five distinct sparse computation strategies on Apple M3 Max all fail to outperform dense convolution, because SIMD architectures cannot exploit the fine-grained, unstructured sparsity of i.i.d. binary spikes. Instead, we propose Temporal Aggregated Con...Votes: 0GitHub stars: 3
- Combining Convolution Delay Learning Recurrent SpikingCombining convolutional recurrent connections with DelRec delay learning in spiking neural networks for resource-constrained edge deployment - arXiv:2604.15997 (April 2026). Covers convolutional recurrent SNNs, axonal delay learning, ~99% parameter reduction, 52x inference speedup on audio classification.Votes: 0GitHub stars: 3
- Constraints On Hebbian And Stdp Learned Weights Of A Spiking Neuron**arXiv ID:** 2012.07664 **Authors:** Dominique Chu, Huy Le Nguyen **Published:** 2020-12-14T16:09:12Z **Abstract:** We analyse mathematically the constraints on weights resulting from Hebbian and STDP learning rules applied to a spiking neuron with weight normalisation. In the case of pure Hebbian learning, we find that the normalised weights equal the promotion probabilities of weights up to correction terms that depend on the learning rate and are usually small. A similar relation can be d...Votes: 0GitHub stars: 3
- Conv Delay Learning Recurrent SnnCombining convolutional recurrent connections with DelRec delay learning mechanism for streamlined SNN architecture, achieving 99% recurrent parameter savings and 52x faster inference on audio classification tasks.Votes: 0GitHub stars: 3
- Convolution Delay Recurrent SnnCombining convolutional recurrent connections with delay learning (DelRec extension) in spiking neural networks. Achieves 99% recurrent parameter savings, 52x faster inference while retaining accuracy. Evaluated on audio classification tasks.Votes: 0GitHub stars: 3
- Current Injection Spiking Neural NetworkCurrent Injection Spiking Neural Network (CIS-Fuse) methodology for infrared and visible image fusion. Introduces the current injection spiking (CIS) operator that performs cross-modal fusion directly at the membrane-potential level, preserving subthreshold responses from both modalities before spike firing. Use when implementing energy-efficient multi-modal image fusion with spiking neural networks.Votes: 0GitHub stars: 3
- Deep Reinforcement Learning With Spiking Qlearning**arXiv ID:** 2201.09754 **Authors:** Ding Chen, Peixi Peng, Tiejun Huang, Yonghong Tian **Published:** 2022-01-21T16:42:11Z **Abstract:** With the help of special neuromorphic hardware, spiking neural networks (SNNs) are expected to realize artificial intelligence (AI) with less energy consumption. It provides a promising energy-efficient way for realistic control tasks by combining SNNs with deep reinforcement learning (RL). There are only a few existing SNN-based RL methods at present. Mos...Votes: 0GitHub stars: 3
- Dendritic Balance Learning局部树突平衡学习框架。抑制性神经元学习平衡单个树突隔室的兴奋性输入， 使突触可塑性学习高效表示。 触发词：树突平衡、突触可塑性、表示学习、脉冲神经网络、dendritic balance、 synaptic plasticity, representation learning, spiking neural network。Votes: 0GitHub stars: 3
- Dendritic Icl SnnDendriCL methodology for dendritic in-context learning in single-layer spiking neural networks. Demonstrates that a single dendritic compartment with online-LMS dynamics is sufficient for general-purpose ICL without attention, depth, or inference-time plasticity.Votes: 0GitHub stars: 3
- Dendritic In Context Learning SnnDendriCL methodology for in-context learning in single-layer spiking neural networks using dendritic compartment dynamics. Use when: implementing ICL in biologically-plausible SNNs, designing compartmental spiking architectures, studying online LMS in dendrites, or building seed-stable ICL at super-dimensional task complexity. arXiv: 2607.02289Votes: 0GitHub stars: 3
- Dic Neuron Reconstruction Spike TimesDeep learning + Dynamic Input Conductances (DICs) methodology for fast reconstruction of degenerate conductance-based neuron populations from spike times alone, enabling scalable and interpretable inference from experimental recordings.Votes: 0GitHub stars: 3
- Dual Timescale Memory Snn AstrocyteDual-timescale memory in spiking neuron-astrocyte networks for efficient navigation. Combines long-term memory of successful actions with short-term suppression of recently visited locations using astrocyte-mediated modulation. Use when implementing bio-inspired navigation, working memory in SNNs, or astrocyte-neuron interactions. Triggers: dual timescale memory, astrocyte SNN, spiking navigation, neuron-astrocyte network, efficient exploration.Votes: 0GitHub stars: 3
- Dual Timescale Memory Spiking Neuron Astrocyte NavigationDual-timescale memory in spiking neuron-astrocyte networks for efficient navigation - combines STDP-based long-term memory and astrocyte-mediated short-term suppression of recently visited locations. Based on arXiv:2604.15391.Votes: 0GitHub stars: 3
- Dual Timescale Memory Spiking Neuron Astrocyte NetworkDual-timescale memory in spiking neuron-astrocyte networks for efficient navigation. Combines STDP (long-term) with astrocytic calcium transients (short-term) to create Topological-Context Memory. Applicable to neuromorphic robotics, edge AI, and efficient exploration. Activation: astrocyte memory, neuron-astrocyte network, dual-timescale memory, topological context memory, snan navigation, spiking astrocyte, memristive navigationVotes: 0GitHub stars: 3
- Dynamic Neural Manifolds For Flexible Closed Loop Control On NeuromorphicIn biological circuits, sequential neural activity evolves along dynamic, low-dimensional manifolds to enable flexible behavior. Spiking network models link aspects of this sequential activity to feat. Based on arXiv:2607.07373.Votes: 0GitHub stars: 3
- Dynamics Of Specialization In Neural Modules Under Resource Constraints**arXiv ID:** 2106.02626 **Authors:** Gabriel Béna, Dan F. M. Goodman **Published:** 2021-06-04T17:39:36Z **Abstract:** It has long been believed that the brain is highly modular both in terms of structure and function, although recent evidence has led some to question the extent of both types of modularity. We used artificial neural networks to test the hypothesis that structural modularity is sufficient to guarantee functional specialization, and find that in general, this doesn't necessari...Votes: 0GitHub stars: 3
- E S2feat Semantic Guided Spiking Local FeatureE-S2Feat for event camera local features using SNNs.Votes: 0GitHub stars: 3
- Eas Snn Event DetectionSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Efficient Robust Snn Semg Fatigue DetectionA skill for implementing efficient and robust spiking neural networks for surface electromyography (sEMG) based muscle fatigue detection, based on arXiv:2607.11065Votes: 0GitHub stars: 3
- Efficient Uncertainty Estimation In Spiking Neural Networks Via Mcdropout**arXiv ID:** 2304.10191 **Authors:** Tao Sun, Bojian Yin, Sander Bohte **Published:** 2023-04-20T10:05:57Z **Abstract:** Spiking neural networks (SNNs) have gained attention as models of sparse and event-driven communication of biological neurons, and as such have shown increasing promise for energy-efficient applications in neuromorphic hardware. As with classical artificial neural networks (ANNs), predictive uncertainties are important for decision making in high-stakes applications, such ...Votes: 0GitHub stars: 3
- Embodied Neuromorphic Artificial Intelligence For Robotics Perspectives Challenges And Research Development Stack**arXiv ID:** 2404.03325 **Authors:** Rachmad Vidya Wicaksana Putra, Alberto Marchisio, Fakhreddine Zayer, Jorge Dias, Muhammad Shafique **Published:** 2024-04-04T09:52:22Z **Abstract:** Robotic technologies have been an indispensable part for improving human productivity since they have been helping humans in completing diverse, complex, and intensive tasks in a fast yet accurate and efficient way. Therefore, robotic technologies have been deployed in a wide range of applications, ranging fr...Votes: 0GitHub stars: 3
- Encrypted Computation Snn TfheEfficient encrypted computation in Convolutional Spiking Neural Networks using TFHE (Fully Homomorphic Encryption). Exploits discrete spike signals to avoid continuous non-polynomial function limitations of FHE on neural networks. Activation: homomorphic encryption SNN, privacy-preserving neural network, TFHE, encrypted inference, FHE spiking.Votes: 0GitHub stars: 3
- Enforcesnn Enabling Resilient And Energyefficient Spiking Neural Network Inference Considering Approximate Drams For Embedded Systems**arXiv ID:** 2304.04039 **Authors:** Rachmad Vidya Wicaksana Putra, Muhammad Abdullah Hanif, Muhammad Shafique **Published:** 2023-04-08T15:15:11Z **Abstract:** Spiking Neural Networks (SNNs) have shown capabilities of achieving high accuracy under unsupervised settings and low operational power/energy due to their bio-plausible computations. Previous studies identified that DRAM-based off-chip memory accesses dominate the energy consumption of SNN processing. However, state-of-the-art works...Votes: 0GitHub stars: 3
- Eon1 A Braininspired Processor For Nearsensor Extreme Edge Online Feature Extraction**arXiv ID:** 2406.17285 **Authors:** Alexandra Dobrita, Amirreza Yousefzadeh, Simon Thorpe, Kanishkan Vadivel, Paul Detterer, Guangzhi Tang, Gert-Jan van Schaik, Mario Konijnenburg, Anteneh Gebregiorgis, Said Hamdioui, Manolis Sifalakis **Published:** 2024-06-25T05:23:41Z **Abstract:** For Edge AI applications, deploying online learning and adaptation on resource-constrained embedded devices can deal with fast sensor-generated streams of data in changing environments. However, since maintain...Votes: 0GitHub stars: 3
- Even Faster Snn Simulation With Lazyeventdriven Plasticity And Shared Atomics**arXiv ID:** 2107.04092 **Authors:** Dennis Bautembach, Iason Oikonomidis, Antonis Argyros **Published:** 2021-07-08T20:13:54Z **Abstract:** We present two novel optimizations that accelerate clock-based spiking neural network (SNN) simulators. The first one targets spike timing dependent plasticity (STDP). It combines lazy- with event-driven plasticity and efficiently facilitates the computation of pre- and post-synaptic spikes using bitfields and integer intrinsics. It offers higher bandwi...Votes: 0GitHub stars: 3
- Event Driven Fly Inspired Motion DetectionEvent-driven framework for fly-inspired visual motion detection using event cameras and biologically structured neural computationVotes: 0GitHub stars: 3
- Eventbased Shape From Polarization With Spiking Neural Networks**arXiv ID:** 2312.16071 **Authors:** Peng Kang, Srutarshi Banerjee, Henry Chopp, Aggelos Katsaggelos, Oliver Cossairt **Published:** 2023-12-26T14:43:26Z **Abstract:** Recent advances in event-based shape determination from polarization offer a transformative approach that tackles the trade-off between speed and accuracy in capturing surface geometries. In this paper, we investigate event-based shape from polarization using Spiking Neural Networks (SNNs), introducing the Single-Timestep and ...Votes: 0GitHub stars: 3
- Eventqueues Autodifferentiable SnnAutodifferentiable spike event queues for efficient SNN simulation on AI accelerators (CPU, GPU, TPU, LPU). Enables gradient-based training of spiking neural networks with memory-efficient event-driven computation. Activation: spiking neural network, SNN, event queue, autodifferentiable, neuromorphic simulation, AI accelerator.Votes: 0GitHub stars: 3
- Explore Activation Sparsity In Recurrent Llms For Energyefficient Neuromorphic Computing**arXiv ID:** 2501.16337 **Authors:** Ivan Knunyants, Maryam Tavakol, Manolis Sifalakis, Yingfu Xu, Amirreza Yousefzadeh, Guangzhi Tang **Published:** 2025-01-09T19:13:03Z **Abstract:** The recent rise of Large Language Models (LLMs) has revolutionized the deep learning field. However, the desire to deploy LLMs on edge devices introduces energy efficiency and latency challenges. Recurrent LLM (R-LLM) architectures have proven effective in mitigating the quadratic complexity of self-attention,...Votes: 0GitHub stars: 3
- Federated Snn HeterogeneousFederated learning framework for SNNs that addresses temporal resolution mismatch across edge devices. Enables clients to train at local temporal resolution while remaining compatible with global model aggregation.Votes: 0GitHub stars: 3
- Fits Interpretable Spiking NeuronsFiTS (Frequency Selectivity and Temporal Shaping) interpretable spiking neuron methodology. Factorizes temporal computation within each spiking neuron into Frequency Selectivity (FS) and Temporal Shaping (TS) modules. FS parameterizes each neuron's target frequency as the maximizer of its subthreshold magnitude response, while TS reshapes when frequency components contribute to membrane voltage accumulation through group-delay modulation. Use when: designing interpretable SNN neurons, frequen...Votes: 0GitHub stars: 3
- Focus Session Hardware And Software Techniques For Accelerating Multimodal Foundation Models**arXiv ID:** 2604.21952 **Authors:** Muhammad Shafique, Abdul Basit, Muhammad Abdullah Hanif, Alberto Marchisio, Rachmad Vidya Wicaksana Putra, Minghao Shao **Published:** 2026-04-23T05:27:39Z **Abstract:** This work presents a multi-layered methodology for efficiently accelerating multimodal foundation models (MFMs). It combines hardware and software co-design of transformer blocks with an optimization pipeline that reduces computational and memory requirements. During model development, it...Votes: 0GitHub stars: 3
- Fractional Order SnnSkill for AI agent capabilitiesVotes: 0GitHub stars: 3
- Functional Ensembles Deep Spiking NetworksFunctional Ensembles as Units of Computation in Deep Spiking Networks. 分析深度脉冲神经网络中功能连接组的计算单元作用，通过一阶功能连接（1FC）组揭示信息编码机制。Activation: functional ensemble, 1FC group, spiking neural network, functional connectivity, information encoding, deep SNN, rare events cofiring.Votes: 0GitHub stars: 3
- Fuzzy Spiking Q Learning Autonomous DrivingFuzzy encoder-decoder for spiking Q-networks in autonomous driving. Trainable fuzzy membership functions generate population-based spike representations. Closes performance gap between spiking and non-spiking networks. Activation: spiking Q-learning, fuzzy encoding, autonomous driving, SNN reinforcement learning.Votes: 0GitHub stars: 3
- Gelneuro Neuromorphic Tactile SystemFully integrated sensing-computing neuromorphic visuo-tactile system for texture recognition on edge hardwareVotes: 0GitHub stars: 3
- Gemst Spiking TransformerGe²mS-T 多维分组脉冲 Transformer 架构。通过时间、空间和网络结构三维分组计算，解决 S-ViT 的内存、准确率和能耗三角困境，实现超高能效。Votes: 0GitHub stars: 3
- General Aspects Internal Noise Spiking NeuralInternal noise analysis in Spiking Neural Networks. Covers noise sources (channel, synaptic, threshold), propagation mechanisms, and effects on SNN dynamics. Distinguishes additive vs multiplicative noise regimes and their impacts on computation. Activation: SNN, internal noise, spiking neural networks, noise analysis, neuromorphicVotes: 0GitHub stars: 3
- General Aspects Internal Noise SpikingAnalysis of internal noise in spiking neural networks: how intrinsic noise sources affect SNN dynamics, reliability, and computation. Covers stochastic spiking, channel noise, and noise-driven dynamics. Activation: spiking neural networks, internal noise, stochastic spiking, SNN reliability, channel noise, neural noise, snn dynamicsVotes: 0GitHub stars: 3
- Geometryaware Spiking Graph Neural Network**arXiv ID:** 2508.06793 **Authors:** Bowen Zhang, Genan Dai, Hu Huang, Long Lan **Published:** 2025-08-09T02:52:38Z **Abstract:** Graph Neural Networks (GNNs) have demonstrated impressive capabilities in modeling graph-structured data, while Spiking Neural Networks (SNNs) offer high energy efficiency through sparse, event-driven computation. However, existing spiking GNNs predominantly operate in Euclidean space and rely on fixed geometric assumptions, limiting their capacity to model comple...Votes: 0GitHub stars: 3
- Globally Optimal Snn Parameter ReconstructionGlobally optimal Spiking Neural Network (SNN) training via parameter reconstruction methodology. Extends convexification of parallel feedforward threshold networks to parallel recurrent threshold networks, which subsume parallel SNNs as a structured special case. Proposes parameter reconstruction algorithm that eliminates surrogate gradient approximation errors. Use when training SNNs without surrogate gradients, seeking globally optimal solutions, or addressing SNN training approximation err...Votes: 0GitHub stars: 3
- Globally Optimal Snn TrainingGlobally optimal SNN training via parameter reconstruction. Convexifies parallel recurrent threshold networks (subsuming parallel SNNs) and uses parameter reconstruction to avoid surrogate gradient approximation errors. Use when training SNNs without surrogate gradients or seeking globally optimal solutions.Votes: 0GitHub stars: 3
- Gradientfree Continual Learning In Spiking Neural Networks Via Interspike Interval Regularization**arXiv ID:** 2604.16496 **Authors:** Samrendra Roy, Kazuma Kobayashi, Souvik Chakraborty, Sajedul Talukder, Syed Bahauddin Alam **Published:** 2026-04-14T03:16:26Z **Abstract:** Continual learning, the ability to acquire new tasks sequentially without forgetting prior knowledge, is essential for deploying neural networks in dynamic real-world environments, from nuclear digital twin monitoring to grid-edge fault detection. Existing synaptic importance methods, such as Elastic Weight Consolida...Votes: 0GitHub stars: 3
- Grouped Spiking Transformer Gemmst分组脉冲Transformer (Ge²mS-T) - 多维分组策略实现超高能效。将脉冲神经网络应用于Transformer架构，通过分组自注意力降低计算复杂度。适用于边缘设备部署和神经形态计算。激活: spiking transformer, grouped attention, energy efficient, neuromorphic computingVotes: 0GitHub stars: 3
- H2learn Snn AcceleratorHigh-efficiency hardware accelerator for BPTT-based Spiking Neural Network training. Design LUT-based processing elements, dual-sparsity-aware backward engine, and pipeline optimization. Achieve 7.38x area saving, 10.20x speedup vs GPU.Votes: 0GitHub stars: 3
- Hardware Aware Mixed Signal Snn FrameworkOpen-source hardware-aware simulation framework for mixed-signal SNNs enabling comparative analysis across neuron models (LIF, HH, AH), synapse types (floating-gate, ReRAM), and architectures. Reports accuracy with hardware metrics (area, power, quantization sensitivity).Votes: 0GitHub stars: 3
- Integer State Dynamics Quantized Spiking NeuralSpiking neural networks (SNNs) support energy-efficient machine intelligence because event-driven computation and sparse activity map naturally to low-power digital hardware. In pr... Activation: quantized, integer-state, SNN, hardware, lattice field theory, statistical mechanicsVotes: 0GitHub stars: 3
- Intrinsic Neurosynaptic Memristive SpikingSelf-organizing memristive networks generating neuronal population spiking dynamics with intrinsic neuro-synaptic resonanceVotes: 0GitHub stars: 3