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.
Geometric obstruction framework for multiparameter quantum metrology — identifies when simultaneous t^-2 scaling fails and how to circumvent bottlenecks via adaptive quantum control. Use when designing multiparameter quantum sensors, analyzing Fisher…
Geometric Quantum Physics-Informed Neural Network (GQPINN) methodology for solving PDEs with symmetry-aware quantum circuits. Combines geometric quantum machine learning with physics-informed neural networks. Use when solving PDEs with quantum circuits,…
Geometry-Aware Framework for noninvasive whole human brain dynamics mapping. Incorporates individual cortical geometry into electrophysiology for accurate spatiotemporal reconstruction of brain activity. Activation: geometry-aware, brain dynamics mapping,…
Geometric Basis Functions (GBF) v2 framework for noninvasive whole human brain dynamics mapping. Incorporates individual cortical geometry for accurate spatiotemporal reconstruction at orders of magnitude faster than deep learning.
Enhanced Geometry-Aware Brain Dynamics Mapping using Geometric Basis Functions (GBF) for noninvasive whole-brain spatio-temporal dynamics mapping. Covers basis function construction on brain manifolds, spectral decomposition for multi-scale neural dynamics,…
Geometry-Aware Spiking Graph Neural Network combining SNN energy efficiency with Riemannian manifold learning for non-Euclidean graph structures
GeoSAE methodology for interpretable brain MRI foundation model annotation using geometry-guided sparse autoencoders with age-deconfounded partial correlations. Prevents SAE feature collapse in deep transformer layers, extracts biomarkers from frozen brain…
Analysis of high-temperature Gibbs states with rapid mixing and external field effects. Studies entanglement structure, computational complexity, and thermalization dynamics. Use when: (1) Analyzing Gibbs states at high temperature, (2) Studying external…
Global mean-amplitude feedback-enhanced spiking neural network coherent ising machine (GFSNN-CIM) with physics-driven amplitude stabilization. Solves Max-Cut with 27% improvement vs conventional SNN-CIM, validated on traffic assignment problems. Based on…
Graph Neural Network approach for decoding visual category representations from large-scale brain functional networks using 7T fMRI data.
Research methodology from paper 'Goxpyriment: A Go Framework for Behavioral and Cognitive Experiments'. arXiv:2604.15245v1. Covers key techniques and approaches for neuroscience research. Activation: goxpyriment, go, framework, q-bio.NC
有效脑连接的因果核建模方法（GP CaKe）。结合积分-微分方程和因果核， 使用高斯过程回归非参数学习，实现因果推断。 触发词：有效连接、因果核、脑连接、高斯过程、GP CaKe、 effective connectivity, causal kernel, Gaussian process, brain connectivity。
Source text: Mixed languages
Inter-areal predictive coding for gradient-free continual learning in spiking neural networks. Brain-inspired learning rule using feedback connections to transmit prediction errors without backpropagation. Keywords: gradient-free learning, continual learning,…
Low-rank evolution strategies for gradient-free spiking neural network training. EGGROLL method reduces memory from O(mn) to O(r(m+n)) enabling on-chip learning without surrogate gradients. Key benefits: 2.23x speedup, neuromorphic hardware compatibility, no…
Gradient-Routed Auxiliary Modules (GRAM) methodology for surgical control of dual-use knowledge in AI models. Enables removable knowledge compartments without retraining separate models.
脑连接网络的图拉普拉斯去噪方法。用于提升功能连接估计的可靠性，增强脑状态检测和 BCI 应用的性能。触发词：脑连接去噪、图拉普拉斯、Laplacian denoising、功能连接、FC denoising、J-divergence。
Source text: Chinese
Edge-specific signal propagation on 3D mechanism graphs for quantum yield prediction. Uses graph neural networks to predict fluorescent protein quantum yields from chromophore-region structural graphs.
Analyze and optimize graph pooling operations by examining the interaction between node features and graph topology. Ensures effective pooling in GNN-based graph classification.
Graph-regularized deep learning framework for EEG-based emotion recognition with psychologically-grounded label structure. Introduces Graph Label Smoothing, Graph Laplacian Commuting Distance, and Sliced Wasserstein Distance regularization strategies. Use…
Rippled graphene nanopores as fluidic memristive devices with synaptic and neuromorphic functionalities. Bio-inspired ion channel-based computing using nanofluidic memristors. Activation: graphene memristor, fluidic memristive, ion channel computing,…
Research methodology from paper 'Gravitational-wave lensing beyond rays: a disordered-system approach'. arXiv:2604.15313v1. Covers key techniques and approaches for neuroscience research. Activation: gravitational, wave, lensing, astro-ph.CO
规范网格细胞理论综述：探讨网格细胞表征的计算原理和神经编码。涵盖路径整合、生物合理性编码、非线性解码及任务优化神经网络整合。适用于计算神经科学、神经编码研究、空间导航机制。
Source text: Chinese
First unified recurrent network model implementing Dale's Law (every neuron is either excitatory or inhibitory) that trains via masked next-observation prediction to co-emerge both grid and place cells from a single architecture. Use when researching: grid…
A unified recurrent network model instantiating Dale's Law where grid cells and place cells co-emerge from a single sensory-prediction objective without supervision of either type — the first such model to explain co-emergence, grid fragmentation, wall…
脑临界性的 Griffiths 相框架。扩展的临界区域解释个体变异， 平衡鲁棒性与灵活性。结合结构网络模块性和区域异质性。 触发词：脑临界性、Griffiths相、临界点、个体变异、鲁棒性与灵活性、 brain criticality, Griffiths phase, critical point, individual variability。
Source text: Mixed languages
Methodology for analyzing and mitigating grokking, epoch-wise double descent, and late-stage generalization decay in overparameterized quantum neural networks via weight-norm regularization.
Differentiable cost terms for breadth, depth, and time in recurrent convolutional neural networks. Jointly optimizes spatial/temporal resource costs with task errors to produce adaptive computational graphs that grow organically through training.
Differentiable cost framework for jointly optimizing neural network breadth, depth, and time - reveals resource trade-offs and human reaction time correlation
GSU-DBNet: Dual-Branch Spiking Neural Network for neuromorphic speech enhancement with Gated Spiking Units (GSU). Achieves PESQ 3.04 with only 394K params (4.5-10.6% of ANN models). (arXiv: 2606.23761)
Quantum-inspired Hamiltonian optimization for QKD network routing using effective Hamiltonian modeling, Quantum Monte Carlo annealing, and stochastic Tensor Network State compression. Activation: QKD routing, Hamiltonian optimization, tensor networks, quantum…
Hamiltonian-encoded quantum reservoir computing methodology for robust quantum learning on NISQ platforms. Addresses trainability (barren plateaus), hardware efficiency, and information stability through direct Hamiltonian mapping and quantum dynamical…
Extremely slow scaling of minimal Hamming distance in quantum sampling data. Use when analyzing quantum algorithms, complexity bounds, quantum ML architectures, or quantum error correction involving mathematical analysis and statistical methods.
Humanoid Agentic Task-Space Whole-Body Control via Distilled Complementary Teachers - 多教师KL蒸馏框架用于人形机器人全身控制
Source text: Chinese
Hardware-aware open-source framework for mixed-signal Spiking Neural Network design space exploration. Captures non-ideal analog/digital hardware behavior while supporting system-level exploration for energy-efficient neuromorphic edge computing. Activation:…
Hardware-aware QAOA methodology for cybersecurity applications. Combines hardware noise modeling, error-mitigated expectation estimation, and application-specific problem formulation for 100+ qubit NISQ processors.
Hardware-aware open-source simulation framework for mixed-signal spiking neural networks. Enables cross-layer design space exploration across neuron models (LIF, HH, AH), synaptic devices (floating-gate, ReRAM), and architectures. Reports accuracy alongside…
Hardware-aware analysis methodology for Variational Quantum Algorithms (VQAs). Analyzes how hardware compilation (transpilation, qubit mapping, gate decomposition) fundamentally alters expressibility and trainability of parameterized quantum circuits (PQCs).…
Hardware-faithful formal verification for IEC 61131-3 PLC programs on resource-constrained microcontrollers. Closes the deployment gap between abstract verification models and real MCU hardware by using declarative HAL descriptors (word width, ADC/PWM…
Helmholtz-SDE仿真自由潜在随机微分方程变分推断方法。通过优化与规定边缘分布兼容的路径定律，闭合近似差距，在高后验不确定性下更忠实恢复动力学。
Source text: Chinese
HERMES脑连接分析工具箱。整合功能和有效连接分析方法，包括互相关、相干性、Granger因果、相位同步、互信息等。适用于EEG/MEG脑网络分析、神经生理信号处理。触发词：HERMES、脑连接、功能连接、有效连接、Granger因果、相位同步、brain connectivity、effective connectivity。
Source text: Chinese