All categories
DevOps & Cloud
Deployment, cloud, containers, CI/CD, monitoring, and infrastructure
- 20,289
- 846
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 devops & cloud skills
Showing 7,177–7,200 of 20,289 skills
- Surrogate Gradient Snn TrainingSurrogate Gradient Learning for Spiking Neural Networks - comprehensive training framework using differentiable surrogate functions to overcome the non-differentiability of spike functions. Includes multiple surrogate gradient types (fast-sigmoid, exponential, arctan, erf), temporal batch normalization, neuron normalization, and advanced training strategies for deep SNNs. Activation: surrogate gradient SNN, differentiable spike, spiking neural network training, SNN backpropagation, time surro...Votes: 0GitHub stars: 3
- Sumo Whole Body LocomanipulationSim-to-real approach for dynamic whole-body loco-manipulation with test-time steering. Use when: (1) Designing legged robot control systems, (2) Implementing dynamic manipulation with heavy objects, (3) Building generalizable locomotion policies, (4) Transferring simulation-trained policies to real robots. Triggers: legged robots, whole-body control, loco-manipulation, sim-to-real transfer, dynamic manipulation, test-time steering, policy generalization.Votes: 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
- 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 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 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 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
- Spiketimer Snn Copyright ProtectionActive copyright protection for Spiking Neural Networks via temporal backdoor regularizationVotes: 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
- 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 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 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 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 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
- Signal Transform UnificationUnify signal transforms (DFT, DCT, wavelet, KLT, etc.) under representation-theoretic principles via the Algebraic Diversity framework. Covers matched group discovery, Peter-Weyl theorem applications, covariance-invariant transforms, and applications to MIMO, GNNs, transformers, and quantum informatics. Activation: signal transform theory, matched group discovery, Algebraic Diversity, DFT unification, representation theory signal processing, Peter-Weyl transform, covariance eigenbasis.Votes: 0GitHub stars: 3
- Sandbox Digital Twin CpsSandbox-Enabled Digital Twin for Cyber-Physical Systems (CPS) - closed-loop validation framework that captures controller side-channels with simulated plant feedbackVotes: 0GitHub stars: 3
- Realtime Snn Object Detection EdgeReal-time object detection with Spiking Neural Networks on edge neuromorphic hardware. Covers SNN architecture design, ANN-to-SNN distillation training, and deployment on Intel Loihi 2. Trigger words: SNN object detection, neuromorphic object detection, Loihi 2 deployment, event-based detection, edge SNN detection, SNN distillation training.Votes: 0GitHub stars: 3
- Realm Lfp Retrospective DecodingREALM methodology for LFP-based behavior decoding using retrospective distillation. Use when: building causal LFP decoding models, offline-to-online distillation for neural signals, Mamba-based neural sequence modeling, BCI decoding without spike signals, reducing bandwidth/power in implantable BCIs, behavior decoding from local field potentials. Activation: LFP decoding, REALM, retrospective distillation, causal neural decoding, wireless BCI, Mamba neural model, spike-free decoding.Votes: 0GitHub stars: 3
- Quantum Sensor ReliabilityImprove quantum sensor network reliability through RL-optimized dynamical decoupling (DD) pulse sequences. Use when mitigating environmental decoherence in quantum sensors, optimizing DD pulse sequences, designing hybrid quantum-classical sensing pipelines, or addressing noise-aware control in quantum sensor networks. Applies to quantum sensing, quantum-classical HPC integration, and noise-adaptive quantum control systems.Votes: 0GitHub stars: 3
- Quantized Snn Hardware OptimizationQuantized Spiking Neural Network Hardware Optimization - techniques for integer-state SNNs, hardware acceleration, and energy-efficient neuromorphic computing. Activation: quantized SNN, hardware SNN, neuromorphic optimization, energy-efficient spiking network, integer-state SNN, SNN quantization.Votes: 0GitHub stars: 3
- Quantization Spiking Neural Networks Beyond AccuracyEMD-based evaluation framework for SNN quantization that goes beyond accuracy metrics. Activation: SNN quantization, Earth Mover's Distance, temporal dynamics preservation.Votes: 0GitHub stars: 3
- Qmaxcal Open Quantum ControlPath-space regularization for open quantum control using Girsanov's theorem. Use when designing quantum control policies under decoherence, computing trajectory likelihood ratios for monitored quantum systems, or optimizing open quantum system control via stochastic path integrals. Combines Girsanov change-of-measure with quantum trajectory theory for differentiable KL divergence estimation.Votes: 0GitHub stars: 3
- Qlif Cast Quantum Spiking ForecastingQuantum Leaky-Integrate-and-Fire (QLIF-CAST) methodology for time-series forecasting. Adapts QLIF spiking neural networks for multivariate regression, achieving 15.4% lower MSE than classical LIF and 94% faster convergence than QLSTM/QNN. Activated by: quantum spiking forecasting, QLIF, time-series quantum, quantum regression.Votes: 0GitHub stars: 3
- Q Spirl Quantum Spiking RlQ-SpiRL: Quantum Spiking Reinforcement Learning framework combining spike-based temporal processing with variational quantum feature transformation for adaptive robot navigation and control. Use when: quantum reinforcement learning, spiking neural network RL, quantum spiking systems, robot navigation policies, quantum-enhanced SNN.Votes: 0GitHub stars: 3