All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Fqpdr Quantum Medical DiagnosisFederated Quantum Neural Network (FQN) methodology for privacy-preserving medical diagnosis. Combines federated learning with quantum neural networks for distributed healthcare data analysis without centralizing patient data. Use when: building privacy-preserving AI for medical imaging, deploying quantum ML across hospitals, handling sensitive patient data with quantum advantage, federated learning for clinical diagnosis. Activation: federated quantum, quantum medical diagnosis, FQN, privacy-...Votes: 0GitHub stars: 3
- Frequency Matching Snn MmwaveFrequency-matching methodology for Spiking Neural Networks in mmWave sensing. LIF dynamics provide inherent low-pass filtering that suppresses high-frequency noise in mmWave signals. Derives principled criterion for membrane decay factor by matching LIF effective bandwidth to data's discriminative spectral content. Use when applying SNNs to sensor data with frequency structure, configuring SNN temporal filtering, or optimizing edge perception systems. Trigger: mmWave SNN, frequency matching L...Votes: 0GitHub stars: 3
- Friedman Nemenyi Eeg Bci BenchmarkStatistical benchmarking methodology for EEG motor-imagery BCI decoders using Friedman-Nemenyi tests. Proves no single decoding pipeline dominates across subjects — personalized model selection adds ~7% accuracy over best fixed choice. Use when evaluating BCI decoders, comparing multi-classifier performance, or designing subject-aware BCI systems.Votes: 0GitHub stars: 3
- Frontend Best PracticesSenior Front-End Developer guidance for ReactJS, NextJS, JavaScript, TypeScript, HTML, CSS and modern UI/UX frameworks. Use when building front-end applications, writing React/Next.js code, or implementing UI components. Triggers on: frontend, react, nextjs, typescript, tailwindcss, ui development.Votes: 0GitHub stars: 3
- Frontier Qldpc DecoderFrontier decoder for quantum LDPC codes — pruned dynamic-programming approach with narrow frontier syndrome decoding. Uses prefix merging with same residual syndrome and logical label, approximates logical-coset posteriors by retaining scored frontier. Achieves near-optimal thresholds for surface code and color code with linear complexity at constant list size. arXiv:2606.20513. Activates: qldpc decoding, frontier decoder, quantum error correction, sparse quantum decoding, syndrome decoding, ...Votes: 0GitHub stars: 3
- Fsd Rm Small Data RepresentationFSD-RM for small-data representation learning with NAS.Votes: 0GitHub stars: 3
- Ft Primitive BenchFTPrimitiveBench methodology for fault-tolerant quantum computing benchmarking. Provides systematic approach for evaluating QEC protocols under hardware-motivated noise models including Pauli bias, measurement bias, and spatio-temporal non-uniformity. Use when: (1) analyzing fault-tolerant quantum computing performance, (2) benchmarking QEC codes under realistic noise, (3) comparing decoders for surface code, (4) studying logical primitive operations (memory, lattice surgery, Hadamard, phase ...Votes: 0GitHub stars: 3
- Ftqc Encoding Circuit SynthesisEncoding circuit synthesis methodology for fault-tolerant quantum computation. Constructs optimized circuits that map arbitrary logical states into error-correcting codes, minimizing two-qubit gate count and circuit depth. Use when: (1) designing fault-tolerant state preparation circuits, (2) encoding logical qubits into QECCs, (3) optimizing encoding circuit overhead, (4) compiling general-state preparation for FTQC.Votes: 0GitHub stars: 3
- Full Extractors Hgp QldpcFull extractor construction for logical processing in Hypergraph Product (HGP) QLDPC codes. Enables Pauli-based computation without compilation overhead. Extractors 50-80% of base code size, max qubit degree 10, fault-tolerant. arXiv:2606.03507.Votes: 0GitHub stars: 3
- Full Stack Fp4 PretrainingFull-Stack FP4 pretraining framework — first complete NVFP4 LLM pretraining resolving stability bottlenecks in linear projections (LoRA-SVD), optimizers (AdamW second-moment transform, Muon Newton-Schulz), and attention (mixed-precision with forward-backward alignment).Votes: 0GitHub stars: 3
- Functional Connectivity Graph Neural NetworksFunctional Connectivity Graph Neural Networks methodology combining structural and functional connectivity with persistent graph homology for brain-inspired graph classification. Activation triggers: functional connectivity, graph neural network, persistent homology, brain network, multi-modal GNN.Votes: 0GitHub stars: 3
- Functional Connectome Fingerprint功能性连接组指纹分析方法论。扩展 differential identifiability 框架， 检测个体指纹梯度和双胞胎指纹梯度。 触发词：脑指纹、连接组指纹、个体差异、可识别性、fingerprint、 differential identifiability, connectome fingerprint。Votes: 0GitHub stars: 3
- Functional Ensembles Deep Spiking NetworksFunctional Ensembles as Units of Computation in Deep Spiking Networks. 1FC (first-order functionally-connected) ensembles framework for analyzing information encoding in SNNs through rare coordinated firing events.Votes: 0GitHub stars: 3
- Functional Ensembles Snn ComputationFunctional ensembles as units of computation in deep spiking networks. First-order functionally-connected (1FC) groups based on pairwise correlations, aggregate cofiring predicts downstream responses, ReLU-like input-output relationship with ensemble-size scaling, rare high-coordination events encode information. Activation: functional ensemble, SNN computation, functional connectivity, 1FC group, ensemble cofiring, deep spiking network analysis.Votes: 0GitHub stars: 3
- Functional Proximity Law MultilayerFunctional Proximity Law in Multilayer Networks: Hub importance scores persist more strongly between functionally similar layers. Validated across 17 pre-registered experiments including neuroscience (r=0.777 in C. elegans connectome). Activation: multilayer networks, functional proximity, hub importance, network layers, cross-layer similarity.Votes: 0GitHub stars: 3
- Functional Whole Brain Models FwbmFunctional Whole-Brain Models (fWBMs) — unified framework integrating structural/dynamical realism with functional competenceVotes: 0GitHub stars: 3
- Functional Whole Brain ModelsFunctional Whole-Brain Models (FWBM) methodology bridging bottom-up whole-brain modeling and top-down neuroconnectionism. Combines biophysically detailed simulations with functional-performance-driven deep neural networks. Use when: designing brain-scale computational models, integrating structure and function in neural modeling, building neuroconnectionist models with biological grounding, developing hybrid brain models that achieve both biological fidelity and functional competence. Activat...Votes: 0GitHub stars: 3
- Funessian Process Non MarkovianFunessian过程：一种连续时间正可分非马尔可夫过程，具有初始状态记忆。平稳态下关联函数指数衰减（通常被视为马尔可夫特征），但记忆贯穿演化。互信息作为非马尔可夫性度量。应用于随机游走，展示记忆效应打破遍历性并改变扩散系数。Votes: 0GitHub stars: 3
- Game Energetic Ei NetworksGame-theoretic energetic framework for excitatory-inhibitory neural circuits with asymmetric connectivity and stability analysis.Votes: 0GitHub stars: 3
- Game Theoretic Socio Technical ControlGame-theoretic frameworks for modeling, learning, and control in socio-technical systems. Covers cooperative/noncooperative paradigms, feedback learning, incentive mechanism design, and multi-agent resilience. Tutorial by Tamer Başar, Tomohisa Hayakawa, Hideaki Ishii, Quanyan Zhu. Activation: game-theoretic control, socio-technical systems, multi-agent resilience, incentive design, Stackelberg games, cooperative games, mechanism designVotes: 0GitHub stars: 3
- Gated Qkan FwpQuantum-inspired sequence learning using Gated QKAN-FWP (Quantum Fast Weight Programmers with variational quantum Kolmogorov-Arnold Networks). Use this skill for designing quantum-inspired sequence models, temporal encoding for quantum ML, fast weight programming patterns, and Kolmogorov-Arnold Network architectures for sequential data. Also triggered by: quantum sequence learning, QKAN, fast weight programmer, quantum-inspired RNN, temporal encoding quantum, 量子序列学习.Votes: 0GitHub stars: 3
- Gaussian GrpoGaussian Group Relative Policy Optimization (G²RPO) for multimodal RL training. Replaces linear scaling with distributional matching to ensure gradient equity across diverse tasks. Use when training multimodal models, balancing perception vs reasoning, or stabilizing RL across heterogeneous reward topologies. Keywords: G²RPO, Gaussian GRPO, multimodal RL, entropy shaping, response length shaping, GRPO, reinforcement learning.Votes: 0GitHub stars: 3
- Gear Grounding Evidence Aware RewardGrounding Evidence-Aware Reward for Long-Context Reasoning to Reduce Repetitive CopyingVotes: 0GitHub stars: 3
- Gem Quantum Error MitigationGeneralized Error Mitigation (GEM) framework for quantum computing - zero-noise extrapolation-free error mitigation using measurement statistics. Reduces effective circuit depth by learning noise-free output distribution from noisy measurements. Use when: quantum error mitigation, zero-noise extrapolation, near-term quantum computing, NISQ device noise reduction, quantum noise characterization, scalable quantum algorithms, GEM framework, randomized compiling.Votes: 0GitHub stars: 3
- Gemst Multidimensional Grouping SnnGe²mS-T: Multi-Dimensional Grouping for Ultra-High Energy Efficiency in Spiking Transformers. Temporal, spatial, and channel grouping for efficient S-ViT training and inference. Triggers: spiking transformer, S-ViT, energy efficiency, multi-dimensional grouping, SNN.Votes: 0GitHub stars: 3
- Genco Unified Neural Solver Grid AnalysisGENCO unified neural solver for power grid analysis.Votes: 0GitHub stars: 3
- Gene Bench Experience ControlStrategy Gene methodology for experience-driven test-time control in LLM agents. Compact control-oriented experience representation (~230 tokens) outperforms documentation-heavy Skill (~2500 tokens) by +3.0pp. Core principle: encode experience as control signal, not documentation. Includes GEP protocol for gene evolution, AVOID directive patterns, and selective experience accumulation. Trigger: experience reuse, test-time control, skill representation, agent memory, experience evolution, stra...Votes: 0GitHub stars: 3
- A Bayesian Neural Network Based On Dropout Regulation**arXiv ID:** 2102.01968 **Authors:** Claire Theobald, Frédéric Pennerath, Brieuc Conan-Guez, Miguel Couceiro, Amedeo Napoli **Published:** 2021-02-03T09:39:50Z **Abstract:** Bayesian Neural Networks (BNN) have recently emerged in the Deep Learning world for dealing with uncertainty estimation in classification tasks, and are used in many application domains such as astrophysics, autonomous driving...BNN assume a prior over the weights of a neural network instead of point estimates, enabling ...Votes: 0GitHub stars: 3
- A Bioinspired Chaos Sensor Model Based On The Perceptron Neural Network Machine Learning Concept And Application For Computational Neuroscience**arXiv ID:** 2306.01991 **Authors:** Andrei Velichko, Petr Boriskov, Maksim Belyaev, Vadim Putrolaynen **Published:** 2023-06-03T03:36:47Z **Abstract:** The study presents a bio-inspired chaos sensor model based on the perceptron neural network for the estimation of entropy of spike train in neurodynamic systems. After training, the sensor on perceptron, having 50 neurons in the hidden layer and 1 neuron at the output, approximates the fuzzy entropy of a short time series with high accuracy,...Votes: 0GitHub stars: 3
- A Generalized Framework For Population Based Training**arXiv ID:** 1902.01894 **Authors:** Ang Li, Aleksandra Spyra, Sagi Perel, Valentin Dalibard, Max Jaderberg, Chenjie Gu, David Budden, Tim Harley, Pramod Gupta **Published:** 2019-02-05T20:11:17Z **Abstract:** Population Based Training (PBT) is a recent approach that jointly optimizes neural network weights and hyperparameters which periodically copies weights of the best performers and mutates hyperparameters during training. Previous PBT implementations have been synchronized glass-box sys...Votes: 0GitHub stars: 3
- A Graph Is Worth 1bit Spikes When Graph Contrastive Learning Meets Spiking Neural Networks**arXiv ID:** 2305.19306 **Authors:** Jintang Li, Huizhe Zhang, Ruofan Wu, Zulun Zhu, Baokun Wang, Changhua Meng, Zibin Zheng, Liang Chen **Published:** 2023-05-30T16:03:11Z **Abstract:** While contrastive self-supervised learning has become the de-facto learning paradigm for graph neural networks, the pursuit of higher task accuracy requires a larger hidden dimensionality to learn informative and discriminative full-precision representations, raising concerns about computation, memory footpr...Votes: 0GitHub stars: 3
- A Layer Wise Interactive Dual Stream Network For EElectroencephalography (EEG) provides a non-invasive window into brain activity, offering high temporal resolution crucial for understanding and interacting with neural processes through brain-compute...Votes: 0GitHub stars: 3
- A Review Of Some Techniques For Inclusion Of Domainknowledge Into Deep Neural Networks**arXiv ID:** 2107.10295 **Authors:** Tirtharaj Dash, Sharad Chitlangia, Aditya Ahuja, Ashwin Srinivasan **Published:** 2021-07-21T18:18:02Z **Abstract:** We present a survey of ways in which existing scientific knowledge are included when constructing models with neural networks. The inclusion of domain-knowledge is of special interest not just to constructing scientific assistants, but also, many other areas that involve understanding data using human-machine collaboration. In many such ins...Votes: 0GitHub stars: 3
- A Theoretical Framework For Inference And Learning In Predictive Coding Networks**arXiv ID:** 2207.12316 **Authors:** Beren Millidge, Yuhang Song, Tommaso Salvatori, Thomas Lukasiewicz, Rafal Bogacz **Published:** 2022-07-21T04:17:55Z **Abstract:** Predictive coding (PC) is an influential theory in computational neuroscience, which argues that the cortex forms unsupervised world models by implementing a hierarchical process of prediction error minimization. PC networks (PCNs) are trained in two phases. First, neural activities are updated to optimize the network's respon...Votes: 0GitHub stars: 3
- A Unified Framework For Soft Threshold Pruning**arXiv ID:** 2302.13019 **Authors:** Yanqi Chen, Zhengyu Ma, Wei Fang, Xiawu Zheng, Zhaofei Yu, Yonghong Tian **Published:** 2023-02-25T08:16:14Z **Abstract:** Soft threshold pruning is among the cutting-edge pruning methods with state-of-the-art performance. However, previous methods either perform aimless searching on the threshold scheduler or simply set the threshold trainable, lacking theoretical explanation from a unified perspective. In this work, we reformulate soft threshold pruning...Votes: 0GitHub stars: 3
- Adamz An Enhanced Optimisation Method For Neural Network Training**arXiv ID:** 2411.15375 **Authors:** Ilia Zaznov, Atta Badii, Alfonso Dufour, Julian Kunkel **Published:** 2024-11-22T23:33:41Z **Abstract:** AdamZ is an advanced variant of the Adam optimiser, developed to enhance convergence efficiency in neural network training. This optimiser dynamically adjusts the learning rate by incorporating mechanisms to address overshooting and stagnation, that are common challenges in optimisation. Specifically, AdamZ reduces the learning rate when overshooting i...Votes: 0GitHub stars: 3
- Adaptive Directional Gradient QcForward gradient estimation methodology for training parameterised quantum circuits (PQCs). Introduces QUIVER adaptive optimiser that recovers SPSA, random coordinate descent, and parameter-shift rule as limiting cases. Enables efficient training of 60-qubit quantum neural networks.Votes: 0GitHub stars: 3
- Adversarial Feature Learning**arXiv ID:** 1605.09782 **Authors:** Jeff Donahue, Philipp Krähenbühl, Trevor Darrell **Published:** 2016-05-31T19:37:29Z **Abstract:** The ability of the Generative Adversarial Networks (GANs) framework to learn generative models mapping from simple latent distributions to arbitrarily complex data distributions has been demonstrated empirically, with compelling results showing that the latent space of such generators captures semantic variation in the data distribution. Intuitively, models ...Votes: 0GitHub stars: 3
- Agilenet Lightweight Dictionarybased Fewshot Learning**arXiv ID:** 1805.08311 **Authors:** Mohammad Ghasemzadeh, Fang Lin, Bita Darvish Rouhani, Farinaz Koushanfar, Ke Huang **Published:** 2018-05-21T22:36:11Z **Abstract:** The success of deep learning models is heavily tied to the use of massive amount of labeled data and excessively long training time. With the emergence of intelligent edge applications that use these models, the critical challenge is to obtain the same inference capability on a resource-constrained device while providing ada...Votes: 0GitHub stars: 3
- Amplifying Human Performance In Combinatorial Competitive Programming**arXiv ID:** 2411.19744 **Authors:** Petar Veličković, Alex Vitvitskyi, Larisa Markeeva, Borja Ibarz, Lars Buesing, Matej Balog, Alexander Novikov **Published:** 2024-11-29T14:40:36Z **Abstract:** Recent years have seen a significant surge in complex AI systems for competitive programming, capable of performing at admirable levels against human competitors. While steady progress has been made, the highest percentiles still remain out of reach for these methods on standard competition platfor...Votes: 0GitHub stars: 3
- An Accurate And Fullyautomated Ensemble Model For Weekly Time Series Forecasting**arXiv ID:** 2010.08158 **Authors:** Rakshitha Godahewa, Christoph Bergmeir, Geoffrey I. Webb, Pablo Montero-Manso **Published:** 2020-10-16T04:29:09Z **Abstract:** Many businesses and industries require accurate forecasts for weekly time series nowadays. However, the forecasting literature does not currently provide easy-to-use, automatic, reproducible and accurate approaches dedicated to this task. We propose a forecasting method in this domain to fill this gap, leveraging state-of-the-art...Votes: 0GitHub stars: 3
- An Adaptive And Near Parameterfree Evolutionary Computation Approach Towards True Automation In Automl**arXiv ID:** 2001.10178 **Authors:** Benjamin Patrick Evans, Bing Xue, Mengjie Zhang **Published:** 2020-01-28T05:44:53Z **Abstract:** A common claim of evolutionary computation methods is that they can achieve good results without the need for human intervention. However, one criticism of this is that there are still hyperparameters which must be tuned in order to achieve good performance. In this work, we propose a near "parameter-free" genetic programming approach, which adapts the hyperp...Votes: 0GitHub stars: 3
- An Algorithmic Framework For The Optimization Of Deep Neural Networks Architectures And Hyperparameters**arXiv ID:** 2303.12797 **Authors:** Julie Keisler, El-Ghazali Talbi, Sandra Claudel, Gilles Cabriel **Published:** 2023-02-27T08:00:33Z **Abstract:** In this paper, we propose an algorithmic framework to automatically generate efficient deep neural networks and optimize their associated hyperparameters. The framework is based on evolving directed acyclic graphs (DAGs), defining a more flexible search space than the existing ones in the literature. It allows mixtures of different classical o...Votes: 0GitHub stars: 3
- An Effective Algorithm For Hyperparameter Optimization Of Neural Networks**arXiv ID:** 1705.08520 **Authors:** Gonzalo Diaz, Achille Fokoue, Giacomo Nannicini, Horst Samulowitz **Published:** 2017-05-23T20:17:44Z **Abstract:** A major challenge in designing neural network (NN) systems is to determine the best structure and parameters for the network given the data for the machine learning problem at hand. Examples of parameters are the number of layers and nodes, the learning rates, and the dropout rates. Typically, these parameters are chosen based on heuristic r...Votes: 0GitHub stars: 3
- An Optimal Control Approach For Neural Network Architecture Adaptation With AThis work presents a novel approach for adapting neural network architecture along the depth based on a posteriori error estimation. By formulating neural network training as a continuous-time optimal. Based on arXiv:2607.07637.Votes: 0GitHub stars: 3
- Analog Interaction Systems AisAnalog Interaction Systems (AIS) methodology for energy-efficient generative modeling on neuromorphic hardware. Bridges gap between software-defined generative models and fixed physics-determined differential equations in analog circuits. Use when designing low-power generative models, implementing analog/neuromorphic computing for ML, optimizing energy-efficient AI hardware, or working with oscillator-based dynamical systems.Votes: 0GitHub stars: 3
- Anomaly Localization In Model Gradients Under Backdoor Attacks Against Federated Learning**arXiv ID:** 2111.14683 **Authors:** Zeki Bilgin **Published:** 2021-11-29T16:46:01Z **Abstract:** Inserting a backdoor into the joint model in federated learning (FL) is a recent threat raising concerns. Existing studies mostly focus on developing effective countermeasures against this threat, assuming that backdoored local models, if any, somehow reveal themselves by anomalies in their gradients. However, this assumption needs to be elaborated by identifying specifically which gradients ar...Votes: 0GitHub stars: 3
- Applying Guidance In A Limited Interval Improves Sample And Distribution Quality In Diffusion Models**arXiv ID:** 2404.07724 **Authors:** Tuomas Kynkäänniemi, Miika Aittala, Tero Karras, Samuli Laine, Timo Aila, Jaakko Lehtinen **Published:** 2024-04-11T13:16:47Z **Abstract:** Guidance is a crucial technique for extracting the best performance out of image-generating diffusion models. Traditionally, a constant guidance weight has been applied throughout the sampling chain of an image. We show that guidance is clearly harmful toward the beginning of the chain (high noise levels), largely unn...Votes: 0GitHub stars: 3
- Arbitrary Order Metalearning With Simple Populationbased Evolution**arXiv ID:** 2303.09478 **Authors:** Chris Lu, Sebastian Towers, Jakob Foerster **Published:** 2023-03-16T16:55:26Z **Abstract:** Meta-learning, the notion of learning to learn, enables learning systems to quickly and flexibly solve new tasks. This usually involves defining a set of outer-loop meta-parameters that are then used to update a set of inner-loop parameters. Most meta-learning approaches use complicated and computationally expensive bi-level optimisation schemes to update these me...Votes: 0GitHub stars: 3
- Are All Vision Models Created Equal A Study Of The Openloop To Closedloop Causality Gap**arXiv ID:** 2210.04303 **Authors:** Mathias Lechner, Ramin Hasani, Alexander Amini, Tsun-Hsuan Wang, Thomas A. Henzinger, Daniela Rus **Published:** 2022-10-09T16:56:45Z **Abstract:** There is an ever-growing zoo of modern neural network models that can efficiently learn end-to-end control from visual observations. These advanced deep models, ranging from convolutional to patch-based networks, have been extensively tested on offline image classification and regression tasks. In this paper, ...Votes: 0GitHub stars: 3