All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Neurostorm Fmri FoundationNeuroSTORM - Neuroimaging Foundation Model with Spatial-Temporal Optimized Representation for fMRI analysis. Trained on 28.65M frames from 50,000 subjects using shifted scanning Mamba backbone. Activation triggers: fMRI foundation model, neuroimaging, NeuroSTORM, brain analysis, Mamba fMRI, spatial-temporal modeling.Votes: 0GitHub stars: 3
- Neurosymbolic Ai An Emerging Class Of Ai Workloads And Their Characterization**arXiv ID:** 2109.06133 **Authors:** Zachary Susskind, Bryce Arden, Lizy K. John, Patrick Stockton, Eugene B. John **Published:** 2021-09-13T17:19:59Z **Abstract:** Neuro-symbolic artificial intelligence is a novel area of AI research which seeks to combine traditional rules-based AI approaches with modern deep learning techniques. Neuro-symbolic models have already demonstrated the capability to outperform state-of-the-art deep learning models in domains such as image and video reasoning. T...Votes: 0GitHub stars: 3
- Neurosymbolic Visual Reasoning Disentangling Visual From Reasoning**arXiv ID:** 2006.11524 **Authors:** Saeed Amizadeh, Hamid Palangi, Oleksandr Polozov, Yichen Huang, Kazuhito Koishida **Published:** 2020-06-20T08:48:29Z **Abstract:** Visual reasoning tasks such as visual question answering (VQA) require an interplay of visual perception with reasoning about the question semantics grounded in perception. However, recent advances in this area are still primarily driven by perception improvements (e.g. scene graph generation) rather than reasoning. Neuro-sym...Votes: 0GitHub stars: 3
- Neurotrain Local Learning Snn BenchmarkingNeuroTrain: Survey and benchmarking framework for SNN local learning rules. Comprehensive taxonomy of SNN training algorithms spanning surrogate-gradient backpropagation, local/three-factor learning, biologically inspired plasticity, ANN-to-SNN conversion, and non-standard optimization. Includes open-source benchmarking framework built on snnTorch for reproducible cross-method comparison. Activation: neurotrain, SNN training survey, spiking neural network benchmark, local learning rules, SNN ...Votes: 0GitHub stars: 3
- Neurotrain Snn BenchmarkingComprehensive SNN training algorithm taxonomy and open benchmarking framework from NeuroTrain paper (arXiv:2605.15058). Covers surrogate-gradient backpropagation, local/three-factor learning rules, predictive coding, and neuromodulated plasticity. Use when: analyzing SNN training methods, comparing learning rules, benchmarking spiking networks, evaluating biological plausibility vs computational efficiency, implementing local learning in SNNs.Votes: 0GitHub stars: 3
- Neurrate Neural Semantic NarrationNEURRATOR (神经叙述器) - 从单个神经元活动生成自然语言描述的框架，实现单细胞分辨率视觉语义叙述Votes: 0GitHub stars: 3
- Neurrator Neural Semantic NarrationNEURRATOR - Semantic narration of vision at single-cell resolution. Decodes spiking activity into natural-language descriptions using CLIP embeddings and multimodal language models.Votes: 0GitHub stars: 3
- Neutral Theory Neural Dynamics中性理论无标度神经动力学方法论。神经元雪崩无标度行为不源于临界性，而是来自中性漂移。适用于脑网络雪崩分析、临界性研究、神经动力学建模。触发词：中性理论、无标度、神经元雪崩、临界性、neutral theory、scale-free、neural avalanche。Votes: 0GitHub stars: 3
- Ng Nmm Brain DynamicsNext Generation Neural Mass Models (NG-NMM) for emergent spatiotemporal dynamics in large-scale brain networks. Captures exact macroscopic gamma activity of coupled excitatory/inhibitory populations with Master Stability Function analysis. Activation triggers: neural mass model, NG-NMM, spatiotemporal dynamics, brain network, gamma oscillations, PING mechanism, whole-brain model.Votes: 0GitHub stars: 3
- Nm Pruning Spiking Neural NetworksProbability-based N:M semi-structured pruning for Spiking Neural Networks from scratch. Uses basis-logit parameterization and eligibility-inspired distillation (EID) for hardware-amenable sparsity patterns. Activation: N:M pruning SNN, SpikeNM, semi-structured spiking pruning, probability pruning SNN.Votes: 0GitHub stars: 3
- Noise Accelerated Kramers Neural ManifoldNoise-accelerated Kramers escape and coherence resonance methodology for 5D neural manifolds. Stochastic dynamics analysis for neural state transitions. Activation: kramers escape, coherence resonance, neural manifold noise, stochastic neural dynamics.Votes: 0GitHub stars: 3
- Noise Field Partial FunctionalizationNoise-modulated neural networks using spatial noise fields for partial functionalization. Structured noise activates overlapping subnetworks, enabling multi-function storage in single networks. Activation: noise field neural network, partial functionalization, spatial noise, subnetwork selection, noise-modulated computation, 噪声场神经网络, 部分功能化.Votes: 0GitHub stars: 3
- Noisy Snn Learning噪声驱动脉冲神经网络学习框架。将噪声作为计算资源利用，引入Noisy SNN (NSNN)和Noise-Driven Learning (NDL)规则，提升鲁棒性和概率计算能力。适用于神经形态计算、鲁棒AI、概率神经编码。触发词：噪声SNN、噪声驱动学习、概率计算、鲁棒性、noisy spiking neural network、noise-driven learning、NSNN、NDL、probabilistic neural coding。Votes: 0GitHub stars: 3
- Non Hermitian Qudit SimulatorsEngineering non-Hermitian k-body interactions in digital qudit quantum simulators using SU(d) gate decomposition with O(d²) gate count scaling.Votes: 0GitHub stars: 3
- Nonequilibrium Brain Dynamics PhysicsComprehensive review of nonequilibrium physics in neuroscience. Analyzes time-irreversibility, entropy production, and broken detailed balance in neural dynamics as signatures of cognitive complexity and consciousness.Votes: 0GitHub stars: 3
- Nonequilibrium Brain DynamicsNonequilibrium physics framework for brain dynamics analysis. Covers entropy production, time-irreversibility, broken detailed balance, and nonequilibrium computation in neural systems. Use when analyzing brain dynamics from nonequilibrium statistical physics perspective, measuring entropy production, studying time-irreversibility in neural data, or investigating consciousness/cognitive complexity through nonequilibrium metrics.Votes: 0GitHub stars: 3
- Nonlocal Operator Fmri EncodingNeural integral operator framework for fMRI encoding and decoding tasks — uses latent neural integral operators with fixed-point iterations to model spatiotemporal brain dynamics, with systematic analysis of spatiotemporal context effects on performance and latent-space geometry.Votes: 0GitHub stars: 3
- Nonstabilizerness Diffusive DynamicsNonstabilizerness diffusion dynamics methodology for analyzing magic resource generation in many-body quantum systems using stabilizer Renyi entropy and tensor network methods.Votes: 0GitHub stars: 3
- Object Detection Recognition Deep Learning And The Universal Law Of Generalization**arXiv ID:** 2206.05365 **Authors:** Faris B. Rustom, Haluk Öğmen, Arash Yazdanbakhsh **Published:** 2022-06-10T22:26:29Z **Abstract:** Object detection and recognition are fundamental functions underlying the success of species. Because the appearance of an object exhibits a large variability, the brain has to group these different stimuli under the same object identity, a process of generalization. Does the process of generalization follow some general principles or is it an ad-hoc "bag-of...Votes: 0GitHub stars: 3
- Odebrain Continuous Eeg GraphNeural ODE latent dynamic forecasting framework for continuous-time EEG graph modeling. Overcomes discrete-time RNN limitations by using Neural ODEs to model continuous latent dynamics of brain networks from EEG. Use when modeling neural population dynamics, continuous brain state forecasting, or EEG time-series with Neural ODEs.Votes: 0GitHub stars: 3
- Omnimouse Brain Model ScalingOmniMouse methodology for multi-modal, multi-task brain models at scale. Uses 150B neural tokens dataset to study scaling properties of brain activity modeling, revealing that brain models are data-limited unlike language/vision models. Activation: OmniMouse, brain model scaling, neural tokens, multi-modal brain, mouse visual cortex, data-limited scaling.Votes: 0GitHub stars: 3
- Omnineuro Bci FrameworkOmniNeuro multimodal HCI framework for explainable BCI feedback — integrates Physics (Energy), Chaos (Fractal Complexity), and Quantum-Inspired uncertainty modeling to transform BCI from silent decoder to transparent feedback partner. Use when designing brain-computer interfaces with interpretability, neurofeedback systems, BCI sonification, multimodal BCI feedback, or quantum-inspired uncertainty in neural decoding (arXiv: 2601.00843)Votes: 0GitHub stars: 3
- On The Intrinsic Structures Of Spiking Neural Networks**arXiv ID:** 2207.04876 **Authors:** Shao-Qun Zhang, Jia-Yi Chen, Jin-Hui Wu, Gao Zhang, Huan Xiong, Bin Gu, Zhi-Hua Zhou **Published:** 2022-06-21T09:42:30Z **Abstract:** Recent years have emerged a surge of interest in SNNs owing to their remarkable potential to handle time-dependent and event-driven data. The performance of SNNs hinges not only on selecting an apposite architecture and fine-tuning connection weights, similar to conventional ANNs, but also on the meticulous configuration o...Votes: 0GitHub stars: 3
- Online Damage Recovery For Physical Robots With Hierarchical Qualitydiversity**arXiv ID:** 2210.09918 **Authors:** Maxime Allard, Simón C. Smith, Konstantinos Chatzilygeroudis, Bryan Lim, Antoine Cully **Published:** 2022-10-18T15:02:41Z **Abstract:** In real-world environments, robots need to be resilient to damages and robust to unforeseen scenarios. Quality-Diversity (QD) algorithms have been successfully used to make robots adapt to damages in seconds by leveraging a diverse set of learned skills. A high diversity of skills increases the chances of a robot to succ...Votes: 0GitHub stars: 3
- Online Generalised Predictive CodingOnline Generalised Predictive Coding via Dynamic Expectation Maximisation (ODEM) for biologically plausible online learning. Activation: predictive coding, online learning, DEM, dynamic expectation maximisation, active inference.Votes: 0GitHub stars: 3
- Optical Neural Networks Waveguide QedAll-optical neural networks using coherent transient quantum dynamics in waveguide QED systemsVotes: 0GitHub stars: 3
- Optimal Shadow EstimationOptimal shadow estimation methodology — proving Theta(d^2) bases for worst-case and Theta(d) for average-case, with explicit basis families and 2-design protocols.Votes: 0GitHub stars: 3
- Option Discovery In Hierarchical Reinforcement Learning Using Spatiotemporal Clustering**arXiv ID:** 1605.05359 **Authors:** Aravind Srinivas, Ramnandan Krishnamurthy, Peeyush Kumar, Balaraman Ravindran **Published:** 2016-05-17T20:44:19Z **Abstract:** This paper introduces an automated skill acquisition framework in reinforcement learning which involves identifying a hierarchical description of the given task in terms of abstract states and extended actions between abstract states. Identifying such structures present in the task provides ways to simplify and speed up reinforce...Votes: 0GitHub stars: 3
- Options As Responses Grounding Behavioural Hierarchies In Multiagent Rl**arXiv ID:** 1906.01470 **Authors:** Alexander Sasha Vezhnevets, Yuhuai Wu, Remi Leblond, Joel Z. Leibo **Published:** 2019-06-04T14:18:47Z **Abstract:** This paper investigates generalisation in multi-agent games, where the generality of the agent can be evaluated by playing against opponents it hasn't seen during training. We propose two new games with concealed information and complex, non-transitive reward structure (think rock/paper/scissors). It turns out that most current deep reinfor...Votes: 0GitHub stars: 3
- Orthoreg Hybrid Symbolic Neural DynamicsOrthogonal Regularization 方法论用于混合符号-神经动力系统，防止符号结构被神经网络残余吸收，实现互补分解Votes: 0GitHub stars: 3
- Oscillatory Snn Time Delayed CoordinationOscillatory Spiking Neural Network with time-delayed coordination inspired by cortical synchronous rhythms. Models cortical oscillations as coordination mechanism gating information flow between spiking populations, enabling structured representations through time-delayed STDP. Activation: oscillatory SNN, cortical rhythm learning, time-delayed spike coordination, brain-inspired SNN learning, synchronous rhythm SNN.Votes: 0GitHub stars: 3
- Pa Tcnet Cross Subject EegPA-TCNet methodology for cross-subject motor imagery EEG decoding in stroke patients. Combines pathology-aware temporal calibration (filtering lesion-induced slow-wave artifacts) with physiology-guided target refinement (entropy-based pseudo-label filtering) for robust domain adaptation. Use when: cross-subject EEG decoding, stroke rehabilitation BCI, motor imagery classification with pathological EEG, domain adaptation for EEG, lesion-aware neural decoding, or brain-computer interfaces for n...Votes: 0GitHub stars: 3
- Parallel Scan Neural Quantum StatesParallel Scan Recurrent Neural Quantum States (PSR-NQS) methodology for scalable variational Monte Carlo simulations. Use when designing efficient RNN-based quantum state ansätze, training neural quantum states with autoregressive models, scaling quantum simulations to large 2D spin lattices, or applying parallel scan techniques to sequential quantum architectures.Votes: 0GitHub stars: 3
- Parallelized Hierarchical Connectome Phc并行化层次连接组(PHC)框架：用于脑网络时空循环建模的深度学习架构。结合结构连接和功能连接，通过并行化计算实现大规模脑网络的高效分析。适用于脑网络动力学、神经影像学、脑疾病预测。Votes: 0GitHub stars: 3
- Parallelized Hierarchical Connectome SsmParallelized Hierarchical Connectome (PHC) framework upgrading temporal State-Space Models (SSMs) into spatiotemporal recurrent networks. Maps SSM diagonal core to Neuron Layer and inter-neuronal communication to Synapse Layer, enabling parallel-scan-based brain-scale network simulation with O(T log T) complexity. Use when: brain-scale neural network simulation, spatiotemporal SSMs, connectome-constrained neural modeling, parallel scan recurrent networks, spiking SSMs, or efficient long-seque...Votes: 0GitHub stars: 3
- Parametric Strong Coupling Quantum MemoryParametrically induced strong coupling between superconducting quantum circuits and solid-state spin ensembles. Uses parametric pump to achieve on-demand MHz-rate coupling for quantum state transfer. Enables hybrid quantum memories with coherence beyond superconducting circuits alone. Use when designing quantum memory interfaces, spin-circuit coupling, or parametric quantum interconnects.Votes: 0GitHub stars: 3
- Parrsb Exascale Spectral Element MeshparRSB: Exascale Spectral Element Mesh Partitioning (arXiv: 2606.14659v1). We introduce parRSB - a parallel, highly scalable graph partitioner for spectral...Votes: 0GitHub stars: 3
- Parsimonious Inference On Convolutional Neural Networks Learning And Applying Online Kernel Activation Rules**arXiv ID:** 1701.05221 **Authors:** I. Theodorakopoulos, V. Pothos, D. Kastaniotis, N. Fragoulis **Published:** 2017-01-18T20:03:12Z **Abstract:** A new, radical CNN design approach is presented in this paper, considering the reduction of the total computational load during inference. This is achieved by a new holistic intervention on both the CNN architecture and the training procedure, which targets to the parsimonious inference by learning to exploit or remove the redundant capacity of a...Votes: 0GitHub stars: 3
- Partial Annealing Pattern DecorrelationPartial annealing framework for associative neural networks. Core idea: Coupling neural dynamics with slowly evolving patterns via two-temperature-two-timescale framework introduces real parameter n (replica-like) that tunes fast-slow separation. Negative n induces pattern decorrelation, reducing interference and promoting orthogonality, achieving maximal storage capacity αc=1. Outperforms standard decorrelation on biased patterns. Activation: partial annealing, pattern decorrelation, associa...Votes: 0GitHub stars: 3
- Path Integral Cognition ModelPath Integral Model of Cognition methodology combining quantum physics path integrals with cognitive cost optimization using imaginary-time evolution under projector Hamiltonians and Wick rotation for unitary equivalent representationVotes: 0GitHub stars: 3
- Path Integral Default Intensity PricingPath-integral formalism for semi-analytical pricing of default intensity models in quantitative finance. Enables accurate derivatives pricing (CDS, XVA) under stochastic default intensity without full numerical simulation.Votes: 0GitHub stars: 3
- Pauli Strings Quantum DynamicsInvariant-based analysis of quantum system dynamics using Pauli strings, Lie algebras, and Clifford group symmetries. Use when analyzing quantum circuit reachability, characterizing quantum system dynamics, designing variational quantum algorithms, or studying many-body quantum systems through the lens of Pauli group structure.Votes: 0GitHub stars: 3
- Pca Dmd Neural Dynamics ReconstructionPCA-DMD for neural dynamics reconstruction.Votes: 0GitHub stars: 3
- Pem Ude Neural Governing EquationsPEM-UDE methodology for discovering governing equations from chaotic neural systems. Combines prediction-error method with universal differential equations to extract interpretable mathematical expressions from chaotic dynamical systems, applied to neural population dynamics. Activation: pem-ude, governing equations neural, chaotic system discovery, universal differential equations neural, symbolic regression neural, neural population dynamics discovery.Votes: 0GitHub stars: 3
- Perception Neuroscience Framework Sensorless GazeNeuroscience framework for sensorless gaze-following in HRI. Exploits the brain's convexity prior (hollow-face illusion) to create perceived mutual gaze without sensors, power, or computation. Grounded in STS gaze processing, convexity prior, and predictive processing hierarchy. Use when: human-robot interaction, gaze-following design, low-cost robotics, perceptual illusions in HRI, neuroscience-inspired design, child-robot interaction. Trigger: sensorless gaze, hollow-face illusion, gaze-fol...Votes: 0GitHub stars: 3
- Persistent Homology Brain Connectome ControlPersistent homology methodology for brain network control that broadens controllable subspace by capturing mesoscale integration beyond local connectivity, revealing dissociation between control cost and geometry.Votes: 0GitHub stars: 3
- Persistent Homology Brain Network ControlMethodology for applying persistent homology to brain network control theory, revealing how topological features broaden the controllable subspace beyond what scalar energy measures capture. Use when analyzing brain structural connectomes, network control theory, or topological data analysis in neuroscience contexts.Votes: 0GitHub stars: 3
- Phase Importance Neural Representations Oppenheim LimCausal intervention methodology testing Oppenheim-Lim phase importance asymmetry in deep neural network representations. Phase/sign carries identity while magnitude dispensable; mechanistic explanation for texture-shape gap between CNNs and attention models.Votes: 0GitHub stars: 3
- Phase Model M Current Hippocampal SynchronyPhase model analysis of M-current effects on neural synchrony in hippocampal networks. Theoretical framework linking acetylcholine neuromodulation to neural assembly formation via phase reduction and cluster synchronization.Votes: 0GitHub stars: 3
- Phase Transition Attention BayesianBayesian theory of attention pattern emergence in transformers — derives closed-form posterior over attention matrices, reveals first-order phase transitions in training data amount for copy head emergence, contrasts softmax vs linear attention behavior.Votes: 0GitHub stars: 3