Menu
Skills in this repository
SkillsMP has collected 4,114 skills from hiyenwong/ai_collection. Open a skill to review its source and details.
hiyenwong/ai_collectionShowing 40 of 4,114 collected skills.
Topology-Dependent Emergence of Polychronous Neuronal Groups - Recurrence-plot characterization of how network topology (small-world, scale-free, random) influences the formation and stability of polychronous neuronal groups in spiking neural networks.
Factorized Low-Rank RNN (FacRNN) framework for uncovering independent neural latent dynamics and connectivity. Group-wise independence among latent dimensions with variational autoencoder formulation and partial correlation penalty. Disentangles interpretable…
Mixture-of-Experts (MoE) routing using optimal transport for balanced expert utilization. Region-graph Sinkhorn routing for WSI classification and spatial data. Use when: MoE load balancing, expert routing optimization, spatial token assignment, entropic…
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
Temporal structure analysis of ecological networks for understanding robustness and collapse mechanisms. Methods for modeling plant-pollinator networks with seasonal turnover, analyzing temporal dynamics, detecting bistable regimes, and predicting…
Stability-preserving system identification using Koopman operator lifting with ISS-LMI constraints. Enables data-driven modeling of nonlinear systems (especially Persidskii-class and electromechanical systems) while guaranteeing input-to-state stability. Use…
Stability-goal obfuscation tradeoff methodology for autonomous agents. Addresses the problem that Lyapunov-stable goal-directed trajectories are inherently legible to Bayesian observers, leaking intent. Combines control Lyapunov functions (CLFs),…
arXiv paper search skill - search academic papers by keywords, authors, categories. Supports time filtering, category filtering, and paper detail retrieval. Activation: arxiv search, paper search, 论文搜索, search papers, arxiv 论文.
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
End-to-end academic research workflow using knowledge graphs. Searches papers from arxiv/web, imports to KG database, generates embeddings, runs graph algorithms (PageRank, vector search), and extracts patterns for skill creation. Use for: automated research…
End-to-end academic research workflow using knowledge graphs. Searches papers from arxiv/web, imports to KG database, generates embeddings, runs graph algorithms (PageRank, Louvain, vector search), and extracts patterns for skill creation. Use for: automated…
Comprehensive review of physical neural computing substrates beyond silicon: memristive devices, photonic circuits, mechanical metamaterials, microfluidic networks, and chemical reaction systems. Use when designing neuromorphic hardware, evaluating physical…
Quantum-enhanced EEG signal analysis and neural network foundation model skill. Implements quantum-classical hybrid architectures for brain signal processing, combining quantum encoding layers with classical EEGNet for improved feature extraction from…
Quantum Neural Network Architecture Search (QNAS) skill for designing efficient quantum neural networks on NISQ hardware. Uses multi-objective optimization (NSGA-II) to balance accuracy, runtime efficiency, and circuit cutting overhead. Apply when designing…
Mitigating barren plateaus in Quantum Neural Networks (QNN) via AI-driven framework and advanced initialization strategies. Research skill for NISQ-era quantum machine learning optimization, covering gradient variance analysis, submartingale-based methods,…
Hybrid classical-quantum neural network development skill. Provides workflows for transfer learning, quantum error mitigation, and noise-resistant quantum neural networks. Use when working with quantum machine learning (QML), variational quantum circuits…
Design and optimize quantum neural network architectures based on Lie algebra truncation and parameterized quantum circuit theory. Use when working with quantum machine learning tasks: (1) Designing QNN architectures for classification/regression, (2)…
量子神经科学跨学科分析方法。将量子计算方法应用于神经科学问题，包括量子神经网络(QNN)用于脑信号分析、量子图神经网络(QGNN)用于脑连接、量子算法优化神经动力学建模。激活关键词: quantum neuroscience, quantum neural network, quantum EEG, quantum brain, 量子神经科学, 量子脑科学, QNN neuroscience.
Source text: Chinese
First systematic fairness benchmark for Spiking Neural Networks (SNNs) addressing three dimensions of realism: data bias, spurious feature leakage, and hardware effects. Evaluates fairness-performance trade-offs under resource constraints using four…
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
STARS (Spike Tail-Aware Relational Synthesis) - plug-and-play method for ANN-to-SNN Data-Free Knowledge Distillation (DFKD). Augments BN-guided synthesis with Relational Consistency Alignment and Tail-Aware Regularization. Achieves up to 4.6% improvement on…
Thermodynamic framework for analyzing multiplex neural connectomes, linking synaptic and neuropeptidergic signaling layers. Applied to the complete C. elegans connectome to reveal functional specialization and hierarchical organization through energy-based…
Transport-based mean field theory for spiking neural network population dynamics. Derives approximate macroscopic firing rate evolution from Fokker-Planck transport solutions rather than steady-state assumptions. Use when: studying SNN population
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
[TODO: Complete and informative explanation of what the skill does and when to use it. Include WHEN to use this skill - specific scenarios, file types, or tasks that trigger it.]
Analysis and research synthesis skill for quantum-enhanced medical imaging papers. Use when working with papers on quantum computing for medical image reconstruction (MRI/CT/PET), quantum sensors for diagnostics (NV centers, quantum dots), or quantum…
Quantum machine learning data loading optimization - efficient quantum state preparation, amplitude encoding, and data embedding techniques for QML. Use when: (1) Loading classical data into quantum circuits for QML, (2) Optimizing quantum feature maps and…
Quantum neuromorphic computing framework combining quantum gates, memristive synapses, and quantum cognition for decision making. Use when: (1) analyzing quantum brain models, (2) implementing quantum neural networks, (3) studying quantum cognition…
Quantum computing portfolio optimization skill. Uses QAOA, quantum annealing, and hybrid quantum-classical methods for financial portfolio optimization with higher-order moments (skewness, kurtosis) and real-world constraints (cardinality, turnover limits).…
Systematic 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)…
Intent-based cryptographic API design for post-quantum cryptography (PQC) migration — cryptographic agility patterns for large software portfolios.
Quantum data mining methodologies for information science — frequent itemset mining, quantum pattern discovery, and quantum-enhanced analytics on NISQ devices.
Quantum network routing and entanglement distribution using surface code error correction — reliable quantum communication over noisy channels.
Bilinear gating methodology linking dendritic coincidence detection to motor primitive encoding. Burst fraction encodes goal information selectively, bilinear gate G(g)·Y(s) enables zero-shot generalization in RL agents. Activation: bilinear gating, motor…
QUIET: Edge-centric framework for targeted brain network synchronization. Integrates structural controllability with functional connectivity to identify energy-efficient synchronization pathways. Identifies 'quiet highways' - edges that are structurally…
SC-TauPath 结构连接归因框架用于映射阿尔茨海默病 Tau 传播路径。结合网络扩散模型增强 MLP 与梯度×输入归因，生成多尺度路径图谱（骨干边、高流量路由、枢纽 ROI），验证 Braak 分期解剖学。
Source text: Chinese
本体约束多 LLM 假设评分方法论。使用专家本体（36 个概念）约束本地多 LLM 理事会，对跨学科文献（如预测编码神经科学）进行假设支持评分，生成可审计的分歧测量和定量假设空间映射。
Source text: Chinese
Quantum algorithm for discovering and sampling rare events without prior knowledge of which events are rare. Achieves optimal quantum scaling with rarity threshold and quadratic speedup for heavy-tailed systems.