All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Temporal Coding Thousand Brains SpikingReplaces dense floating-point vectors with rank-order spike packets for sensorimotor object inference in the Monty/Thousand Brains framework. Uses spike-timing-dependent plasticity (STDP) to encode traversal direction and a learnable lambda parameter to adapt integration windows to object geometry. Implemented in ~450 lines of NumPy.Votes: 0GitHub stars: 3
- Tensor Decomposition Brain StatesTensor Decomposition for Dynamic Brain Network StatesVotes: 0GitHub stars: 3
- Texture Interpolation Visual PerceptionTexture Interpolation for Visual PerceptionVotes: 0GitHub stars: 3
- Tgsn Eeg Dementia DiagnosisTask-guided Spatiotemporal Network (TGSN) with diffusion augmentation for EEG-based dementia diagnosis and MMSE prediction. Features multi-band feature fusion, gated spatiotemporal attention module, task-guided query module, and diffusion-based data augmentation. Use for Alzheimer's disease detection, Frontotemporal Dementia classification, VCI assessment, and MMSE score prediction. Keywords: EEG dementia diagnosis, TGSN, task-guided network, spatiotemporal attention, diffusion augmentation, ...Votes: 0GitHub stars: 3
- The Autonomous Agency Scale A Behavioral FrameworkDerived from arXiv:2607.17947 - The Autonomous Agency Scale: A Behavioral Framework for Measuring Self-Directed Behavior in AI SystemsVotes: 0GitHub stars: 3
- The Combined Technique For Detection Of Artifacts In Clinical Electroencephalograms Of Sleeping Newborns**arXiv ID:** 0504070v1 **Authors:** Vitaly Schetinin, Joachim Schult **Published:** 2005-04-14T10:49:55Z **Abstract:** In this paper we describe a new method combining the polynomial neural network and decision tree techniques in order to derive comprehensible classification rules from clinical electroencephalograms (EEGs) recorded from sleeping newborns. These EEGs are heavily corrupted by cardiac, eye movement, muscle and noise artifacts and as a consequence some EEG features are irrelevan...Votes: 0GitHub stars: 3
- The Cooperative Network Architecture Learning Structured Networks As Representation Of Sensory Patterns**arXiv ID:** 2407.05650 **Authors:** Pascal J. Sager, Jan M. Deriu, Benjamin F. Grewe, Thilo Stadelmann, Christoph von der Malsburg **Published:** 2024-07-08T06:22:10Z **Abstract:** We introduce the Cooperative Network Architecture (CNA), a model that represents sensory signals using structured, recurrently connected networks of neurons, termed "nets." Nets are dynamically assembled from overlapping net fragments, which are learned based on statistical regularities in sensory input. This arc...Votes: 0GitHub stars: 3
- The Costs And Benefits Of Goaldirected Attention In Deep Convolutional Neural Networks**arXiv ID:** 2002.02342 **Authors:** Xiaoliang Luo, Brett D. Roads, Bradley C. Love **Published:** 2020-02-06T16:42:00Z **Abstract:** People deploy top-down, goal-directed attention to accomplish tasks, such as finding lost keys. By tuning the visual system to relevant information sources, object recognition can become more efficient (a benefit) and more biased toward the target (a potential cost). Motivated by selective attention in categorisation models, we developed a goal-directed attent...Votes: 0GitHub stars: 3
- The Geometry Of Relu Networks Through The Relu Transition Graph**arXiv ID:** 2505.11692 **Authors:** Sahil Rajesh Dhayalkar **Published:** 2025-05-16T21:00:56Z **Abstract:** We develop a novel theoretical framework for analyzing ReLU neural networks through the lens of a combinatorial object we term the ReLU Transition Graph (RTG). In this graph, each node corresponds to a linear region induced by the network's activation patterns, and edges connect regions that differ by a single neuron flip. Building on this structure, we derive a suite of new theoreti...Votes: 0GitHub stars: 3
- The Impact Of Structural Changes On Learning Capacity In The Fly Olfactory Neural Circuit**arXiv ID:** 2509.19351 **Authors:** Katherine Xie, Gabriel Koch Ocker **Published:** 2025-09-18T00:12:58Z **Abstract:** The Drosophila mushroom body (MB) is known to be involved in olfactory learning and memory; the synaptic plasticity of the Kenyon cell (KC) to mushroom body output neuron (MBON) synapses plays a key role in the learning process. Previous research has focused on projection neuron (PN) to Kenyon cell (KC) connectivity within the MB; we examine how perturbations to the mushro...Votes: 0GitHub stars: 3
- The Neurosymbolic Brain**arXiv ID:** 2205.13440 **Authors:** Robert Lizée **Published:** 2022-05-13T00:39:19Z **Abstract:** Neural networks promote a distributed representation with no clear place for symbols. Despite this, we propose that symbols are manufactured simply by training a sparse random noise as a self-sustaining attractor in a feedback spiking neural network. This way, we can generate many of what we shall call prime attractors, and the networks that support them are like registers holding a symbolic v...Votes: 0GitHub stars: 3
- The Next Big Things In Unsupervised Machine Learning Five Lessons From Infant Learning**arXiv ID:** 2009.08497 **Authors:** Lorijn Zaadnoordijk, Tarek R. Besold, Rhodri Cusack **Published:** 2020-09-17T18:47:06Z **Abstract:** After a surge in popularity of supervised Deep Learning, the desire to reduce the dependence on curated, labelled data sets and to leverage the vast quantities of unlabelled data available recently triggered renewed interest in unsupervised learning algorithms. Despite a significantly improved performance due to approaches such as the identification of di...Votes: 0GitHub stars: 3
- The Unreasonable Effectiveness Of Deep Learning In Artificial Intelligence**arXiv ID:** 2002.04806 **Authors:** Terrence J. Sejnowski **Published:** 2020-02-12T05:25:15Z **Abstract:** Deep learning networks have been trained to recognize speech, caption photographs and translate text between languages at high levels of performance. Although applications of deep learning networks to real world problems have become ubiquitous, our understanding of why they are so effective is lacking. These empirical results should not be possible according to sample complexity in st...Votes: 0GitHub stars: 3
- The Whole Brain Architecture Approach Accelerating The Development Of Artificial General Intelligence By Referring To The Brain**arXiv ID:** 2103.06123 **Authors:** Hiroshi Yamakawa **Published:** 2021-03-06T04:58:12Z **Abstract:** The vastness of the design space created by the combination of a large number of computational mechanisms, including machine learning, is an obstacle to creating an artificial general intelligence (AGI). Brain-inspired AGI development, in other words, cutting down the design space to look more like a biological brain, which is an existing model of a general intelligence, is a promising pla...Votes: 0GitHub stars: 3
- Thermal Equilibrium ConnectomeAlgebraic quantum model where brain functions emerge as thermal equilibrium states of the connectome. Uses KMS formalism and C. elegans connectome. arXiv:2408.14221Votes: 0GitHub stars: 3
- Thermocoherent Cognitive DynamicsThermocoherent framework for modeling information flow in neural matter. Heat flow couples to delocalized information flow carried by shared coherence. Use when: thermocoherent effects in neural systems, quantum cognition physical basis, relational resources in neural tissue (entanglement, discord, classical correlations), Mpemba-type thermal relaxation in cognition, cross-scale neural coordination, arXiv:2604.04069, quantum information flow in neural matter.Votes: 0GitHub stars: 3
- Thermodynamic Brain ConnectivityThermodynamic 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 connectivity analysis.Votes: 0GitHub stars: 3
- Think Aloud Cognitive Model DiscoveryThink-Aloud methodology for automated cognitive model discovery using LLMs. Uses verbal protocol data (think-aloud traces) as additional constraints beyond behavioral data to discover better cognitive models. Activation: think-aloud, cognitive model discovery, verbal protocol, automated model discovery, LLM cognitive modeling, process-level data.Votes: 0GitHub stars: 3
- Three Factor Snn LearningThree-factor learning rules for Spiking Neural Networks - extending STDP with neuromodulatory signals for improved credit assignment, reinforcement learning, and biological plausibility. Comprehensive survey from machine learning perspective. Activation triggers: three-factor learning, SNN learning, neuromodulation, STDP extension, reward learning, dopamine, surrogate gradient.Votes: 0GitHub stars: 3
- Three Layer Quantum Brain CoherenceA coherent research thread across three papers (arXiv:2604.08587, 2603.03345, 2602.16003) establishes a three-layer quantum brain model combining covariant quantum error correction (CQEC) with Lipkin-Meshkov-Glick (LMG) Hamiltonian dynamics. This skill synthesizes the computational patterns for analyzing quantum coherence in biological systems.Votes: 0GitHub stars: 3
- Three Layer Quantum Brain3-Layer Quantum Brain Hypothesis methodology for evaluating quantum error correction in biological systems using radical-pair proteins and covariant purification protocols.Votes: 0GitHub stars: 3
- Time Varying Brain Connectivity时变有向脑网络连接分析方法论。基于 SWpC (sliding-window prediction correlation) 估计动态功能连接，支持方向性信息流分析。 触发词：脑网络、功能连接、动态连接、SWpC、time-varying connectivity、 directed functional connectivity、脑网络分析、神经科学方法。Votes: 0GitHub stars: 3
- Time2 Neural Dynamics Visual PerceptionTime^2 (Time-squared) framework for analyzing neural dynamics of visual perception by simultaneously measuring processing time and stimulus time using reverse correlation methodology. Use when studying visual perception temporal dynamics, rhythmic perception, predictive processing, or coarse-to-fine sampling in neuroscience research.Votes: 0GitHub stars: 3
- Tms Eeg BiomarkersTMS-EEG生物标志物信效度评估方法论。系统评估TMS-EEG标志物的内部可靠性、外部可靠性和有效性，提供评估框架和最佳实践。触发词：TMS-EEG、生物标志物、可靠性、有效性、信效度、TMS biomarkers、reliability、validity、TMS-EEG analysis。Votes: 0GitHub stars: 3
- Tms V5 Mt Modulates Thalamus Visual SpeechTMS modulates thalamus during visual speech recognition.Votes: 0GitHub stars: 3
- Topo Omni Brain Topographic MultimodalDeep topographic multimodal model (Topo-Omni) for discovering functionally selective brain regions with contiguous spatial organization across visual, auditory, and language/cognitive modalities.Votes: 0GitHub stars: 3
- Topo Omni Deep Topographic MultimodalTopo-Omni deep topographic multimodal model for discovering functionally selective brain regions across visual, auditory, and language processing streams. Activation: topographic model, multimodal brain model, cortical organization, brain regions discovery.Votes: 0GitHub stars: 3
- Topological Effective Connectivity HodgeInformation-theoretic framework coupling Hodge decomposition with lead-lag mutual information for directed brain network analysis - separates feed-forward drive, feedback loops, and cyclic flow around topological holes.Votes: 0GitHub stars: 3
- Topological Ml Eeg ClassificationTopological Machine Learning for epileptic iEEG seizure detection using persistent homology and persistence diagrams. Features multiple TDA representations and cross-patient generalization. Activation: topological data analysis, TDA, EEG classification, seizure detection, persistent homology.Votes: 0GitHub stars: 3
- Topological Sensitivity Connectome ConstraintsTopological sensitivity analysis of connectome-constrained neural networks. Studies how network topology affects dynamical behavior and sensitivity to perturbations in brain connectome models. Applicable to robust brain dynamics analysis and lesion studies.Votes: 0GitHub stars: 3
- Topology Dependent Png Recurrence PlotTopology-Dependent Emergence of Polychronous Neuronal Groups via Recurrence Plot characterization. Analyzes how small-world network topology drives PNG formation in spiking networks with STDP and heterogeneous delays.Votes: 0GitHub stars: 3
- Topology Dependent Polychronous Groups RecurrenceTopology-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.Votes: 0GitHub stars: 3
- Topology Dependent Polychronous Neuronal GroupsTopology-Dependent Emergence of Polychronous Neuronal Groups using Recurrence-Plot characterization. Small-world topology as structural optimum for polychronization with label-free PNG identification via sparse-dot-product Recurrence Plot framework.Votes: 0GitHub stars: 3
- Topology Neural Collapse MonitorMonitoring Neural Training with Topology — Footprint-Predictable Collapse Index using Modular Morse Homology Maintenance (MMHM). Detects representational collapse in neural network embeddings before performance metrics degrade. Activation: neural collapse, representational collapse, topological monitoring, training diagnostics, MMHM, embedding degradation, Morse homology.Votes: 0GitHub stars: 3
- Trace Eeg Autoregressive RoutingTRACE (Temporal Routing with Autoregressive Cross-channel Experts) framework for EEG representation learning. Autoregressive pre-training that predicts future EEG patches from causal context using a novel Temporal Routing MoE (TR-MoE) architecture. Key innovation: Cross-Channel Temporal Routing FFN (CTR-FFN) that routes all channels at the same temporal step to the same experts based on causal cross-channel history, preserving instantaneous cross-channel coherence while adapting computation t...Votes: 0GitHub stars: 3
- Traced Activation Cascade AnalysisTRACED: Activation Cascade Root-Cause AnalysisVotes: 0GitHub stars: 3
- Trajectory Controlled InvariantsTrajectory-based computation of controlled invariant sets for linear discrete-time systems and MPC. Use when computing maximal controlled invariant sets, designing MPC without terminal sets, or needing recursive feasibility guarantees. Keywords: controlled invariants, MPC, trajectory-based, convex feasible points, recursive feasibility, terminal sets.Votes: 0GitHub stars: 3
- Trajectory Geometry Transformer RepresentationsTransformer 表征轨迹几何分析方法论 - 将计算神经科学的几何工具应用于 Transformer 可解释性研究，无需探测即可分析表征动力学Votes: 0GitHub stars: 3
- Transcranial Photobiomodulation Insomnia EegTranscranial photobiomodulation (tPBM) therapy for insomnia using EEG biomarkers. Prefrontal cortex near-infrared light stimulation targeting prefrontal hypoactivity and hyperarousal model. Pilot study with college students using EEG spectral analysis and functional connectivity to elucidate therapeutic mechanisms. Use when: neuromodulation therapy, insomnia treatment, EEG biomarkers, photobiomodulation, prefrontal hypoactivity, hyperarousal model, non-invasive brain stimulation, sleep disord...Votes: 0GitHub stars: 3
- Transformer Brain Topological AlignmentUnified geometric space for topological alignment between Transformer-based models and human brain networks. Maps model spatial attention topology to intrinsic connectivity networks (ICNs) for modality-agnostic, task-free comparison. Activation: transformer brain alignment, topological alignment, brain-AI alignment, transformer model alignment, 脑-AI对齐, 拓扑对齐.Votes: 0GitHub stars: 3
- Transport Mean Field Snn DynamicsTransport-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 populationVotes: 0GitHub stars: 3
- Transport Mean Field Snn[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.]Votes: 0GitHub stars: 3
- Traveling Waves Encode The Recent Past And Enhance Sequence Learning**arXiv ID:** 2309.08045 **Authors:** T. Anderson Keller, Lyle Muller, Terrence Sejnowski, Max Welling **Published:** 2023-09-03T22:48:10Z **Abstract:** Traveling waves of neural activity have been observed throughout the brain at a diversity of regions and scales; however, their precise computational role is still debated. One physically inspired hypothesis suggests that the cortical sheet may act like a wave-propagating system capable of invertibly storing a short-term memory of sequential ...Votes: 0GitHub stars: 3
- Treatment Conditioned Diffusion Neurodegenerative ProgressionTreatment-Conditioned Diffusion framework for forecasting neurodegenerative disease progression via high-fidelity brain state prediction. Conditions generative process on DaTscan images and levodopa equivalent daily dose. Activation: neurodegenerative, disease progression, Parkinson, diffusion, longitudinal neuroimaging, DaTscan, treatment-conditioned.Votes: 0GitHub stars: 3
- Tribe Fmri Encoding ValidationValidation methodology for deep multimodal brain-encoding models (TRIBE, the 2025 Algonauts challenge winner) against behavioral engagement metrics. Tests whether predicted fMRI signals forecast aggregate population behavior (YouTube replay heatmaps, neuroforecasting). Shows predicted neural drive fails to predict re-watch despite high encoding accuracy — null result with Bayes factor bounds and equivalence tests. Activation: brain encoding validation, TRIBE, neuroforecasting, predicted fMRI,...Votes: 0GitHub stars: 3
- Tribe Fmri Encoding ValidationValidation framework for brain-encoding models like TRIBE — testing whether predicted fMRI signals correlate with behavioral engagement metrics. Use when evaluating brain-encoding models, testing fMRI predictions against behavioral data, or validating neural prediction models.Votes: 0GitHub stars: 3
- Tribe V2 Multimodal Brain FoundationTRIBE v2 tri-modal foundation model methodology for in-silico neuroscience. Uses video, audio, and language inputs to predict brain activity across diverse experimental conditions. Trained on 1000+ hours of fMRI across 720 subjects. Enables in-silico experimentation and replaces traditional linear encoding models. Activation: TRIBE, tri-modal foundation model, in-silico neuroscience, multimodal brain prediction, video-audio-language fMRI, brain encoding model, naturalistic fMRI, multimodal ne...Votes: 0GitHub stars: 3
- Tribev2 Brain Foundation ModelTRIBE v2: A tri-modal (video, audio, language) foundation model for predicting human brain activity. Use when: building brain encoding models, fMRI prediction, in-silico neuroscience experiments, multimodal brain modeling, analyzing naturalistic fMRI data, or implementing the Algonauts 2025 winning architecture.Votes: 0GitHub stars: 3
- Triple Config Brain Network RnnTriple Configuration Brain Networks framework using RNNs to model EEG source-localized dynamics. Separates exogenous stimuli, task demands, and spontaneous activity contributions to brain network configurations. Identifies parietal network as critical hub. Activation: triple configuration brain, RNN brain network, EEG source localization, parietal hub, brain network configuration, exogenous endogenous brain dynamicsVotes: 0GitHub stars: 3
- Triple Configuration Brain Network RnnTriple Configuration Brain Networks (TCBN) framework using RNNs to model synergistic effects of exogenous stimuli, task demands, and spontaneous activity in brain network reconfiguration. Keywords: brain networks, cognitive flexibility, RNN, task-switching, network dynamics.Votes: 0GitHub stars: 3