All categories
Research
Research, evidence gathering, literature, reports, investigation, and synthesis
- 21,402
- 892
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse research skills
Showing 10,321–10,344 of 21,402 skills
- 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
- 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
- Scaling Up Dynamic Graph Representation Learning Via Spiking Neural Networks**arXiv ID:** 2208.10364 **Authors:** Jintang Li, Zhouxin Yu, Zulun Zhu, Liang Chen, Qi Yu, Zibin Zheng, Sheng Tian, Ruofan Wu, Changhua Meng **Published:** 2022-08-15T09:22:15Z **Abstract:** Recent years have seen a surge in research on dynamic graph representation learning, which aims to model temporal graphs that are dynamic and evolving constantly over time. However, current work typically models graph dynamics with recurrent neural networks (RNNs), making them suffer seriously from compu...Votes: 0GitHub stars: 3
- Scalable Multitask Learning Through Spiking Neural Networks With Adaptive Taskswitching Policy For Intelligent Autonomous Agents**arXiv ID:** 2504.13541 **Authors:** Rachmad Vidya Wicaksana Putra, Avaneesh Devkota, Muhammad Shafique **Published:** 2025-04-18T08:12:59Z **Abstract:** Training resource-constrained autonomous agents on multiple tasks simultaneously is crucial for adapting to diverse real-world environments. Recent works employ reinforcement learning (RL) approach, but they still suffer from sub-optimal multi-task performance due to task interference. State-of-the-art works employ Spiking Neural Networks (...Votes: 0GitHub stars: 3
- Robust Spiking ReservoirRobust Spiking Reservoir Computing methodology for energy-efficient temporal processing. Implements edge-of-chaos tuning with experimental uncertainty handling, bridging abstract criticality notions with practical reservoir computing applications. Based on Freddi et al. (2026) arXiv:2604.06395v1.Votes: 0GitHub stars: 3
- Rhythm Snn Temporal ProcessingNeural oscillation-inspired SNN architecture for enhanced temporal processing and noise robustness. Based on Nature Communications 2025 Rhythm-SNN paper.Votes: 0GitHub stars: 3
- Replay4ncl An Efficient Memory Replaybased Methodology For Neuromorphic Continual Learning In Embedded Ai Systems**arXiv ID:** 2503.17061 **Authors:** Mishal Fatima Minhas, Rachmad Vidya Wicaksana Putra, Falah Awwad, Osman Hasan, Muhammad Shafique **Published:** 2025-03-21T11:33:22Z **Abstract:** Neuromorphic Continual Learning (NCL) paradigm leverages Spiking Neural Networks (SNNs) to enable continual learning (CL) capabilities for AI systems to adapt to dynamically changing environments. Currently, the state-of-the-art employ a memory replay-based method to maintain the old knowledge. However, this te...Votes: 0GitHub stars: 3
- Quantized Snn Beyond AccuracyQuantization of Spiking Neural Networks beyond accuracy - Earth Mover's Distance (EMD) methodology for evaluating SNN quantization effects on spike train distributions, firing patterns, and temporal dynamics. Use when optimizing SNNs for low-precision hardware, analyzing quantization trade-offs in neuromorphic systems. Triggers: SNN quantization, spiking network compression, low-precision SNN, Earth Mover's Distance, neuromorphic hardware optimization.Votes: 0GitHub stars: 3
- Neuromorphic Photonic NeuronselNeuron Surface Emitting Laser (NeuronSEL) — 基于多结VCSEL的神经形态光子脉冲神经元。利用负微分电阻(NDR)实现类神经元的脉冲发放、不应期和整合-发放动力学。适用于光子计算、光通信、神经形态硬件、光学传感。Activation: neuromorphic photonics, VCSEL spiking neuron, negative differential resistance, optical neural network, photonic computing, integrate-and-fire laserVotes: 0GitHub stars: 3
- Neuromorphic Aer Encoder DesignUltra-low-power synthesizable asynchronous AER encoder design for neuromorphic edge devices. Tree-based architecture with bundled-data protocol and cross-coupled NAND random-priority arbiter for event collision resolution. Activation: neuromorphic encoder, AER design, asynchronous circuit, spiking neural network hardware, edge device neuromorphic, low-power SNN.Votes: 0GitHub stars: 3
- Multi Objective Snn OscillationMulti-objective genetic algorithm (NSGA-III) optimisation of recurrent spiking neural networks (RSNNs) to match observed neural firing rates and oscillation frequencies simultaneously, including brain organoid data.Votes: 0GitHub stars: 3
- Morphsnn Adaptive Graph DiffusionMorphSNN: Adaptive graph diffusion and structural plasticity for spiking neural networks. Graph-based SNN with dynamic structure. Activation: morphsnn, graph diffusion, structural plasticity, adaptive snn, graph neural network spiking.Votes: 0GitHub stars: 3
- Memristor Preprocessing ReservoirMemristor-based preprocessing for reservoir computing in image classification. Uses memristor crossbar arrays as reconfigurable nonlinear preprocessing layers to improve accuracy while reducing readout complexity. Keywords: reservoir computing, memristor preprocessing, image classification, crossbar array, nonlinear preprocessing.Votes: 0GitHub stars: 3
- Memristive Spiking Dynamics ResonanceModeling intrinsic neuro-synaptic spiking dynamics and resonance in self-organizing memristive networks. Demonstrates how physical circuits naturally generate neuronal population dynamics similar to biological systems.Votes: 0GitHub stars: 3
- Mar Efficient Large Language Models Via Moduleaware Architecture Refinement**arXiv ID:** 2601.21503 **Authors:** Junhong Cai, Guiqin Wang, Kejie Zhao, Jianxiong Tang, Xiang Wang, Luziwei Leng, Ran Cheng, Yuxin Ma, Qinghai Guo **Published:** 2026-01-29T10:21:28Z **Abstract:** Large Language Models (LLMs) excel across diverse domains but suffer from high energy costs due to quadratic attention and dense Feed-Forward Network (FFN) operations. To address these issues, we propose Module-aware Architecture Refinement (MAR), a two-stage framework that integrates State Spac...Votes: 0GitHub stars: 3
- L Spine Snn Compute EngineL-SPINE 低精度 SIMD 脉冲神经计算引擎方法论。用于资源受限边缘设备的高效 SNN 推理，支持 2/4/8-bit 多精度数据通路，无乘法器 shift-add 模型。适用于神经形态硬件设计、边缘 AI 部署、FPGA SNN 加速。触发词: l-spine, snn hardware, edge inference, low-precision snn, spiking neural compute engineVotes: 0GitHub stars: 3
- Intrinsic Neurosynaptic Spiking MemristiveIntrinsic Neuro-Synaptic Spiking Dynamics in Self-Organizing Memristive Networks (arXiv:2604.18015). Demonstrates that self-assembled memristive networks exhibit intrinsic neuro-synaptic spiking dynamics — including neuronal population bursts, STDP-like learning, emergent oscillatory patterns, multi-modal spike distributions, phase transitions, and criticality signatures — without any external neuron models or transistor-based circuits. Activation: memristive network, spiking dynamics, self-o...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
- 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
- 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
- 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
- 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
- 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
- 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