All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Sbs Self Organization Complex SystemsSurviving by Serving (SBS) principle for self-organization in complex adaptive systems. Components persist when outputs are utilized; non-utilization triggers adaptation. Emergence of functional networks without centralized control.Votes: 0GitHub stars: 3
- Scalable On Hardware Qnn TrainingScalable on-hardware training methodology for Quantum Neural Networks (QNNs) using Butterfly circuit architecture with layer-wise training and parallelized parameter-shift rule. Reduces gradient estimation cost from O(n²) to O(log n), enabling clinical data applications like missing patient data imputation. Validated on IonQ Forte Enterprise at 16 qubits with 32-qubit inference on hardware. Use when: QNN training on quantum hardware, clinical quantum ML, gradient estimation optimization, scal...Votes: 0GitHub stars: 3
- Scalable Open Source Qec SystemOpen-source QEC system architecture using RISC-V-based quantum control with sub-microsecond decoding-feedback latency. FPGA-implemented distributed multi-board architecture for superconducting qubits.Votes: 0GitHub stars: 3
- Scalable Perturbation Learning EsnScalable Perturbation Learning for Online Self-Supervised Echo State Networks - orthogonal decomposition reduces perturbation dimension from reservoir to input dimension, enabling scalable hardware-compatible online learningVotes: 0GitHub stars: 3
- Scaling Laws Beyond Backpropagation**arXiv ID:** 2210.14593 **Authors:** Matthew J. Filipovich, Alessandro Cappelli, Daniel Hesslow, Julien Launay **Published:** 2022-10-26T10:09:14Z **Abstract:** Alternatives to backpropagation have long been studied to better understand how biological brains may learn. Recently, they have also garnered interest as a way to train neural networks more efficiently. By relaxing constraints inherent to backpropagation (e.g., symmetric feedforward and feedback weights, sequential updates), these m...Votes: 0GitHub stars: 3
- Scaling Up Estimation Of Distribution Algorithms For Continuous Optimization**arXiv ID:** 1111.2221 **Authors:** Weishan Dong, Tianshi Chen, Peter Tino, Xin Yao **Published:** 2011-11-09T14:44:58Z **Abstract:** Since Estimation of Distribution Algorithms (EDA) were proposed, many attempts have been made to improve EDAs' performance in the context of global optimization. So far, the studies or applications of multivariate probabilistic model based continuous EDAs are still restricted to rather low dimensional problems (smaller than 100D). Traditional EDAs have difficu...Votes: 0GitHub stars: 3
- Scikit Covtest Covariance Hypothesis Testingscikit-covtest Python package for covariance matrix hypothesis testing across four categories: identity, sphericity, proportionality, and two-sample equality. Provides SciPy-style API for statistical testing of covariance structures in neuroscience, finance, machine learning, and genetics applications including brain connectivity inference, dimensionality reduction, and risk estimation.Votes: 0GitHub stars: 3
- Scores Are Not Decisions Cost Aware Stopping For TScores Are Not Decisions: Cost-Aware Stopping for Tool Acquisition in LLM AgentsVotes: 0GitHub stars: 3
- Sda Qec Diffusion Quantum MedicalSDA-QEC (Simplified Diffusion Augmentation with Quantum-Enhanced Classification) methodology for medical image diagnosis under severe class imbalance. Integrates lightweight diffusion augmentation for minority class rebalancing with quantum feature layers for high-dimensional discrimination. Use when: medical image classification with imbalanced data, quantum-enhanced feature mapping, diffusion data augmentation for healthcare AI. Trigger words: SDA-QEC, diffusion augmentation, quantum-enhanc...Votes: 0GitHub stars: 3
- Sdpc Quantum CloningSemidefinite Programming framework for optimal quantum cloning using Choi-Jamiolkowski isomorphism and primal-dual strong duality certificationVotes: 0GitHub stars: 3
- Seekbrain Autonomous Neuroscience DiscoverySeekBrain autonomous multi-agent framework for accelerating neuroscience discovery using domain-grounded hierarchical planning and cross-modal data analysis. Use when building AI systems for neuroscience research automation.Votes: 0GitHub stars: 3
- Selected Trends In Artificial Intelligence For Space Applications**arXiv ID:** 2212.06662 **Authors:** Dario Izzo, Gabriele Meoni, Pablo Gómez, Dominik Dold, Alexander Zoechbauer **Published:** 2022-12-10T07:49:50Z **Abstract:** The development and adoption of artificial intelligence (AI) technologies in space applications is growing quickly as the consensus increases on the potential benefits introduced. As more and more aerospace engineers are becoming aware of new trends in AI, traditional approaches are revisited to consider the applications of emergin...Votes: 0GitHub stars: 3
- Selectinfer Selective Neuron Loading And ComputatiDerived from arXiv:2607.18081 - SelectInfer: Selective Neuron Loading and Computation for On-Device LLMsVotes: 0GitHub stars: 3
- Selectivity And Shape In The Design Of Forwardforward Goodness Functions**arXiv ID:** 2604.13081 **Authors:** Talha Ruzgar Akkus, Suayp Talha Kocabay, Kamer Ali Yuksel, Hassan Sawaf **Published:** 2026-03-28T23:11:21Z **Abstract:** The Forward-Forward (FF) algorithm trains networks layer-by-layer using a local "goodness function," yet sum-of-squares (SoS) has remained the only choice studied. We systematically explore the goodness-function design space and identify a unifying principle: the goodness function must be sensitive to the shape of neural activity, not ...Votes: 0GitHub stars: 3
- Self Caused Credit Spiking AgencyProposes that **agency-gated slow credit** (conjunctive term `Own*Agency*Salience` driving slow parameter updates) produces **post-unload behavioral residue**: a learned self-preserving choice survives episodic buffer removal.Votes: 0GitHub stars: 3
- Self Modifying Lean Proof Agents With Verifier GroDerived from arXiv:2607.17352 - Self-Modifying Lean Proof Agents with Verifier-Grounded Benchmark CoevolutionVotes: 0GitHub stars: 3
- Self Referential Sat HardnessFinite combinatorial analogue of Gödel's incompleteness theorems within Boolean K-SAT. Proves self-referential hardness exhibits physical invariance precluding quantum shortcuts due to necessity of global semantic analysis, and delineates scaling bottleneck for ML on lossy local compression.Votes: 0GitHub stars: 3
- Selfadaptive Dynamic Integrated Statistical And Information Theory Learning**arXiv ID:** 2211.11491 **Authors:** Zsolt János Viharos, Ágnes Szűcs **Published:** 2022-11-21T14:26:46Z **Abstract:** The paper analyses and serves with a positioning of various error measures applied in neural network training and identifies that there is no best of measure, although there is a set of measures with changing superiorities in different learning situations. An outstanding, remarkable measure called $E_{Exp}$ published by Silva and his research partners represents a research ...Votes: 0GitHub stars: 3
- Selfattentive Neural Collaborative Filtering**arXiv ID:** 1806.06446 **Authors:** Yi Tay, Shuai Zhang, Luu Anh Tuan, Siu Cheung Hui **Published:** 2018-06-17T20:58:12Z **Abstract:** This paper has been withdrawn as we discovered a bug in our tensorflow implementation that involved accidental mixing of vectors across batches. This lead to different inference results given different batch sizes which is completely strange. The performance scores still remain the same but we concluded that it was not the self-attention that contributed to...Votes: 0GitHub stars: 3
- Selfconstructing Neural Networks Through Random Mutation**arXiv ID:** 2103.15692 **Authors:** Samuel Schmidgall **Published:** 2021-03-29T15:27:38Z **Abstract:** The search for neural architecture is producing many of the most exciting results in artificial intelligence. It has increasingly become apparent that task-specific neural architecture plays a crucial role for effectively solving problems. This paper presents a simple method for learning neural architecture through random mutation. This method demonstrates 1) neural architecture may be le...Votes: 0GitHub stars: 3
- Semantic Least Energy Principle IntelligenceThe Semantic Least-Energy Principle (SLEP) hypothesis that intelligent systems evolve internal representations by maximizing semantic utility while minimizing semantic, predictive, and computational energy.Votes: 0GitHub stars: 3
- Semi Device Independent Nlwe CertificationSemi-device-independent certification methodology for nonlocality without entanglement (NLWE) using maximum-confidence discrimination of separable state ensembles.Votes: 0GitHub stars: 3
- Semiclassical Number Theory QuantumSemiclassical methods connecting quantum statistical mechanics to analytic number theory. Uses trace formula and periodic orbit theory to study integer partitions. Activation: semiclassical, integer partitions, density of states, number theory, periodic orbit, trace formula, Pythagorean triples.Votes: 0GitHub stars: 3
- Semidefinite Certificates Pauli HamiltoniansQuantitative semidefinite programming certificates for ground-state energies of Pauli Hamiltonians — explicit finite-level convergence rates for SDP hierarchies in quantum many-body systems. For quantum complexity, optimization, and verification.Votes: 0GitHub stars: 3
- Sensitivity And Generalization In Neural Networks An Empirical Study**arXiv ID:** 1802.08760 **Authors:** Roman Novak, Yasaman Bahri, Daniel A. Abolafia, Jeffrey Pennington, Jascha Sohl-Dickstein **Published:** 2018-02-23T23:11:07Z **Abstract:** In practice it is often found that large over-parameterized neural networks generalize better than their smaller counterparts, an observation that appears to conflict with classical notions of function complexity, which typically favor smaller models. In this work, we investigate this tension between complexity and ge...Votes: 0GitHub stars: 3
- Senworld A Digital Twin Simulation For GeneratingSkill generated from arXiv paper 2607.19949: SenWorld: A Digital-Twin Simulation for Generating Context-Rich Evaluation DataVotes: 0GitHub stars: 3
- Sharma Mittal Entropy GravitySharma-Mittal entropy framework bridging information theory, black hole thermodynamics, and infrared gravity modifications. Derives modified gravitational force laws from generalized entropy, reproduces MOND-like regime. Activates: sharma-mittal entropy, generalized entropy, emergent gravity, MOND, black hole thermodynamics, information bounds, infrared gravity, entropic gravityVotes: 0GitHub stars: 3
- Sherrington Kirkpatrick Game Complex DynamicsComplex dynamics in the Sherrington-Kirkpatrick (SK) game methodology — game-theoretic foundation for adaptive learning in disordered many-player systems with random payoff matrices. Generalizes the SK spin-glass model to game theory with random-field bias, grand-canonical abstention, and convergence/volatility phase diagram. Bridges spin-glass neural network theory, reinforcement learning, and game theory. arXiv:2607.02422Votes: 0GitHub stars: 3
- Shot Based Quantum EncodingShot-Based Quantum Encoding (SBQE) methodology for quantum neural network data loading. Addresses the bottleneck of inefficient data loading on NISQ devices by distributing shots according to data-dependent classical distributions over multiple input states. Use when designing QML data loading strategies, optimizing quantum encoding for near-term hardware, or comparing encoding schemes (angle, amplitude, basis, shot-based). Activation: shot-based encoding, SBQE, quantum data loading, quantum ...Votes: 0GitHub stars: 3
- Shunting Inhibition Dendritic CreditShunting inhibition and dendritic branching reshape local credit assignment geometry. Shows how E/I conductance + dendritic tree structure enable biological neurons to approximate backprop with restricted somatic feedback. By Safaai, Richards & Sabatini (arXiv:2607.03556, July 2026).Votes: 0GitHub stars: 3
- Sign Complex SystemsSparse Identification Graph Neural Network (SIGN) for inferring governing equations of complex networked systems. Use when working with: (1) complex systems dynamics prediction, (2) equation discovery from data, (3) graph neural networks for networked systems, (4) interpretable AI for dynamical systems, (5) large-scale network modeling (climate, biological, technological networks), (6) symbolic regression on graphs. Keywords: SIGN, sparse identification, equation discovery, complex systems, g...Votes: 0GitHub stars: 3
- Silif Dbs Neuromorphic ControllerNeuromorphic silicon neuron controller (SiLIF-DBS) for adaptive deep brain stimulation in Parkinson's Disease — CMOS-implemented closed-loop aDBS achieving 75% power reduction with beta-band biomarker tracking.Votes: 0GitHub stars: 3
- Simulatable Process Learning TheorySimulatable Processes framework for learning under dependent data with access to a simulator. Recovers PAC-style VC-dimension bounds for arbitrarily complex dependent processes, with regret controlled by time-bounded Kolmogorov complexity. COLT 2026 paper. arXiv: 2606.13576Votes: 0GitHub stars: 3
- Single Atom Reservoir ComputingA Single Atom in Front of a Mirror as Universal Reservoir Computer methodology. Demonstrates universality with minimal quantum setup, providing explicit recipe for target accuracy with specified physical resources and resonator modes.Votes: 0GitHub stars: 3
- Singularity Free Invariant ControlSingularity-free dynamical invariants-based quantum control for finite-dimensional state preparation under arbitrary noise. Use when designing invariant-based quantum control protocols, robust state preparation for NISQ hardware, non-Markovian open quantum systems, SU(2) subspace control, or noise-aware control synthesis.Votes: 0GitHub stars: 3
- Skill CreatorGuide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends Claude's capabilities with specialized knowledge, workflows, or tool integrations.Votes: 0GitHub stars: 3
- Skill Drift Contract ViolationProactive maintenance for LLM agent skill libraries by treating skill drift as contract violation. Extracts executable environment contracts from skill documents and validates only role-bearing assumptions against live conditions. Use when: maintaining agent skill libraries, detecting API/dependency changes in reusable skills, reducing false-positive drift monitoring, building CI/CD for agent skill health, or repairing broken skills through contract-based localization. Keywords: skill drift, ...Votes: 0GitHub stars: 3
- Skill ExtractorMeta-skill that extracts reusable skill patterns from conversations and generates standard SKILL.md files.Votes: 0GitHub stars: 3
- Slai T Rex Full Parameter Post Training Of The DeeSkill generated from arXiv paper 2607.20145: SLAI T-Rex: Full-Parameter Post-training of the DeepSeek-V4 Family on Ascend SuperPODVotes: 0GitHub stars: 3
- Sleep Replay Acceleration Sharp**Problem**: Standard sequence models (RNN, Transformers) struggle with long-range non-stationary temporal patterns in strict streaming settings due to: - Truncated backpropagation through time horizon - Explicit input window length constraints - Inability to process sequentially without revisiting past observationsVotes: 0GitHub stars: 3
- Slim Lstms**arXiv ID:** 1812.11391 **Authors:** Fathi M. Salem **Published:** 2018-12-29T16:11:01Z **Abstract:** Long Short-Term Memory (LSTM) Recurrent Neural networks (RNNs) rely on gating signals, each driven by a function of a weighted sum of at least 3 components: (i) one of an adaptive weight matrix multiplied by the incoming external input vector sequence, (ii) one adaptive weight matrix multiplied by the previous memory/state vector, and (iii) one adaptive bias vector. In effect, they augment t...Votes: 0GitHub stars: 3
- Small Free And Effective Orchestrating Open WeightSkill generated from arXiv paper 2607.20216: Small, Free, and Effective: Orchestrating Open-Weight Small Language Models to Outperform Single LLM for Malware AnalysisVotes: 0GitHub stars: 3
- Small Gain Distributed StabilitySmall-gain analysis for large-scale distributed systems - exponential incremental i-IOSS stability via local subsystem conditions. LMI-based stability analysis for nonlinear distributed systems. Activation: distributed stability, small-gain theorem, i-IOSS, nonlinear system stability, large-scale systems.Votes: 0GitHub stars: 3
- Snap Stopping Catastrophic Forgetting In Hebbian Learning With Sigmoidal Neuronal Adaptive Plasticity**arXiv ID:** 2410.15318 **Authors:** Tianyi Xu, Patrick Zheng, Shiyan Liu, Sicheng Lyu, Isabeau Prémont-Schwarz **Published:** 2024-10-20T07:20:33Z **Abstract:** Artificial Neural Networks (ANNs) suffer from catastrophic forgetting, where the learning of new tasks causes the catastrophic forgetting of old tasks. Existing Machine Learning (ML) algorithms, including those using Stochastic Gradient Descent (SGD) and Hebbian Learning typically update their weights linearly with experience i.e., ...Votes: 0GitHub stars: 3
- Snn Online Data Reduction PhysicsSpiking Neural Networks for online data reduction in high-energy physics detectors. Temporal-coincidence encoding and distributed SNN architecture for the ePIC dRICH detector at the Electron-Ion Collider. Achieves 5x data reduction while preserving genuine Cherenkov photon signals against SiPM dark counts.Votes: 0GitHub stars: 3
- Snn Sequence Timing Replay SpeedSpiking Temporal Memory (sTM) model for learning sequence timing and flexible replay speed control - biologically plausible timing encoding via oscillatory modulationVotes: 0GitHub stars: 3
- Socrates Loss Unifying Confidence Calibration And Classification By Leveraging The Unknown**arXiv ID:** 2604.12245 **Authors:** Sandra Gómez-Gálvez, Tobias Olenyi, Gillian Dobbie, Katerina Taškova **Published:** 2026-04-14T03:43:15Z **Abstract:** Deep neural networks, despite their high accuracy, often exhibit poor confidence calibration, limiting their reliability in high-stakes applications. Current ad-hoc confidence calibration methods attempt to fix this during training but face a fundamental trade-off: two-phase training methods achieve strong classification performance at th...Votes: 0GitHub stars: 3
- Soliton Waves Wstdp SnnSoliton-like wave propagation in recurrent spiking neural networks with weighted STDP. Use when studying cortical traveling waves, activity zone delimitation, spatial memory formation, or self-propagating neural activity patterns.Votes: 0GitHub stars: 3
- Sos Distributed TasksDecidability theory for Set of Output Sets (SOS) tasks in asynchronous distributed systems with crash failures. Use when analyzing distributed task solvability, understanding crash tolerance, or designing consensus/set agreement protocols. Keywords: distributed tasks, decidability, crash failures, consensus, set agreement, asynchronous, SOS tasks.Votes: 0GitHub stars: 3
- Sound Localization Equilibrium DynamicsMicrosecond-precision sound localization emerges from slow equilibrium dynamics. ITD represented as stable equilibrium of neural population dynamics rather than classical Jeffress place-coding framework.Votes: 0GitHub stars: 3