All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Chronic Stress Ei Rnn ResilienceComputational modeling methodology for chronic stress as E/I perturbation in recurrent working-memory networks. Identifies enhanced inhibitory-to-excitatory synaptic strength as best-fit mechanism and reveals resilience-generalization trade-off.Votes: 0GitHub stars: 3
- Clane Continual Learning Of Actions On Neuromorphic Hardware From Event Cameras**arXiv ID:** 2605.28387 **Authors:** Elvin Hajizada, Michael Neumeier, Edward Paxon Frady, Yulia Sandamirskaya, Axel von Arnim, Bing Li, Eyke Hüllermeier **Published:** 2026-05-27T12:24:04Z **Abstract:** Recognizing and continuously learning novel human actions without forgetting prior classes is a requirement for emerging AR/VR and robotics applications. For these applications, both on-device processing and learning are essential for privacy and low-latency adaptation. Event cameras address...Votes: 0GitHub stars: 3
- Classification And Generation Of Realworld Data With An Associative Memory Model**arXiv ID:** 2207.04827 **Authors:** Rodrigo Simas, Luis Sa-Couto, Andreas Wichert **Published:** 2022-07-11T12:51:27Z **Abstract:** Drawing from memory the face of a friend you have not seen in years is a difficult task. However, if you happen to cross paths, you would easily recognize each other. The biological memory is equipped with an impressive compression algorithm that can store the essential, and then infer the details to match perception. The Willshaw Memory is a simple abstract mo...Votes: 0GitHub stars: 3
- Closing The Gap Optimizing Guidance And Control Networks Through Neural Odes**arXiv ID:** 2404.16908 **Authors:** Sebastien Origer, Dario Izzo **Published:** 2024-04-25T13:14:32Z **Abstract:** We improve the accuracy of Guidance & Control Networks (G&CNETs), trained to represent the optimal control policies of a time-optimal transfer and a mass-optimal landing, respectively. In both cases we leverage the dynamics of the spacecraft, described by Ordinary Differential Equations which incorporate a neural network on their right-hand side (Neural ODEs). Since the neural ...Votes: 0GitHub stars: 3
- Cog Eeg Agent Autonomous AnalysisLLM-powered EEG analysis agent grounded in MNE-Python that separates semantic interpretation from scientific validation using deterministic contracts and confirmation controls to prevent false positives.Votes: 0GitHub stars: 3
- Cognitive Homeostatic Agents**arXiv ID:** 2103.03359 **Authors:** Amol Kelkar **Published:** 2021-02-27T07:29:43Z **Abstract:** Human brain has been used as an inspiration for building autonomous agents, but it is not obvious what level of computational description of the brain one should use. This has led to overly opinionated symbolic approaches and overly unstructured connectionist approaches. We propose that using homeostasis as the computational description provides a good compromise. Similar to how physiological h...Votes: 0GitHub stars: 3
- Competition Stability Functionality Ei NetworksGame-theoretic energetic framework for asymmetric excitatory-inhibitory neural circuits. Extends energy-based models to E-I networks, revealing competitive dynamics where each neuron minimizes its own energy. Applies network stability principles to Wilson-Cowan and lateral inhibition models.Votes: 0GitHub stars: 3
- Computation With Sequences In A Model Of The Brain**arXiv ID:** 2306.03812 **Authors:** Max Dabagia, Christos H. Papadimitriou, Santosh S. Vempala **Published:** 2023-06-06T15:58:09Z **Abstract:** Even as machine learning exceeds human-level performance on many applications, the generality, robustness, and rapidity of the brain's learning capabilities remain unmatched. How cognition arises from neural activity is a central open question in neuroscience, inextricable from the study of intelligence itself. A simple formal model of neural activ...Votes: 0GitHub stars: 3
- Computational Model Of Music Sight Reading A Reinforcement Learning Approach**arXiv ID:** 1007.0546 **Authors:** Keyvan Yahya, Pouyan Rafiei Fard **Published:** 2010-07-04T12:18:56Z **Abstract:** Although the Music Sight Reading process has been studied from the cognitive psychology view points, but the computational learning methods like the Reinforcement Learning have not yet been used to modeling of such processes. In this paper, with regards to essential properties of our specific problem, we consider the value function concept and will indicate that the optimum ...Votes: 0GitHub stars: 3
- Computer Vision Eeg Artifact RejectionComputer vision based automated ICA rejection for EEG artifact removal with 89.45% accuracy and 7200x speedup over manual inspection. Compatible with ICLabel and EEGLab interfaces.Votes: 0GitHub stars: 3
- Constructing The Umwelt Cognitive Planning Through Beliefintent Coevolution**arXiv ID:** 2511.05540 **Authors:** Shiyao Sang **Published:** 2025-10-30T12:16:45Z **Abstract:** This paper challenges a prevailing epistemological assumption in End-to-End Autonomous Driving: that high-performance planning necessitates high-fidelity world reconstruction. Inspired by cognitive science, we propose the Mental Bayesian Causal World Model (MBCWM) and instantiate it as the Tokenized Intent World Model (TIWM), a novel cognitive computing architecture. Its core philosophy posits ...Votes: 0GitHub stars: 3
- Contravariance Theory Strong Alignment Minimal SolutionsTheory formalizing contravariance in NeuroAI: weak alignment of network representations via affine mappings guarantees strong alignment of privileged axes, and alignment zippers up the network hierarchy. Shows convergent evolution between artificial and brain networks is inevitable for sufficiently hard tasks. Use when working with neuroai, brain-alignment, dnn-brain-comparison.Votes: 0GitHub stars: 3
- Controlled Hierarchical Filtering Model Of Neocortical Sensory Processing**arXiv ID:** 0308025v1 **Authors:** Andras Lorincz **Published:** 2003-08-16T07:31:57Z **Abstract:** A model of sensory information processing is presented. The model assumes that learning of internal (hidden) generative models, which can predict the future and evaluate the precision of that prediction, is of central importance for information extraction. Furthermore, the model makes a bridge to goal-oriented systems and builds upon the structural similarity between the architecture of a rob...Votes: 0GitHub stars: 3
- Cortex Subcortex Memory Limited LearningFramework for functional dissociation between cortical and subcortical systems during learning under memory constraints - cortex supports general structure learning while subcortex specializes in reward-based learningVotes: 0GitHub stars: 3
- Cortiva Eeg Meg Image RetrievalCORTIVA framework for EEG- and MEG-to-image retrieval using candidate-score fusion of complementary visual teachers. Enables zero-shot image retrieval from neural responses by aligning three decoding routes to heterogeneous visual targets, scoring candidates independently, and combining temperature-scaled score vectors before ranking. Use for brain-computer interface applications involving neural decoding, EEG/MEG analysis, and cross-modal retrieval tasks.Votes: 0GitHub stars: 3
- Covariant Qec Quantum BrainCovariant quantum error correction methodology for quantum brain models. Evaluates CQEC purification protocols across radical-pair proteins with ab initio spin Hamiltonians, analyzing layer-specific coherence dynamics and T2 sensitivity.Votes: 0GitHub stars: 3
- Crosslingual Offensive Language Identification For Low Resource Languages The Case Of Marathi**arXiv ID:** 2109.03552 **Authors:** Saurabh Gaikwad, Tharindu Ranasinghe, Marcos Zampieri, Christopher M. Homan **Published:** 2021-09-08T11:29:44Z **Abstract:** The widespread presence of offensive language on social media motivated the development of systems capable of recognizing such content automatically. Apart from a few notable exceptions, most research on automatic offensive language identification has dealt with English. To address this shortcoming, we introduce MOLD, the Marathi O...Votes: 0GitHub stars: 3
- Decoding Listeners Identity Person Identification From Eeg Signals Using A Lightweight Spiking Transformer**arXiv ID:** 2510.17879 **Authors:** Zheyuan Lin, Siqi Cai, Haizhou Li **Published:** 2025-10-17T08:20:01Z **Abstract:** EEG-based person identification enables applications in security, personalized brain-computer interfaces (BCIs), and cognitive monitoring. However, existing techniques often rely on deep learning architectures at high computational cost, limiting their scope of applications. In this study, we propose a novel EEG person identification approach using spiking neural networks ...Votes: 0GitHub stars: 3
- Decoding Semantic Categories Picture Naming Eeg--- created: 2026-06-16 arxiv_id: 2606.14614 authors: Wei Hu, Binbin Xu categories: q-bio.NC, eess.SP published: 2026-06-12 activation: EEG decoding, semantic categories, picture naming, neural decoding, lexical-semantic processing, language production, deep learning, multilingual embeddings ---Votes: 0GitHub stars: 3
- Deep Learning For Sensorbased Activity Recognition A Survey**arXiv ID:** 1707.03502 **Authors:** Jindong Wang, Yiqiang Chen, Shuji Hao, Xiaohui Peng, Lisha Hu **Published:** 2017-07-12T00:21:04Z **Abstract:** Sensor-based activity recognition seeks the profound high-level knowledge about human activities from multitudes of low-level sensor readings. Conventional pattern recognition approaches have made tremendous progress in the past years. However, those methods often heavily rely on heuristic hand-crafted feature extraction, which could hinder thei...Votes: 0GitHub stars: 3
- Deep Neuroevolution To Predict Primary Brain Tumor Grade From Functional Mri Adjacency Matrices**arXiv ID:** 2211.14500 **Authors:** Joseph Stember, Mehrnaz Jenabi, Luca Pasquini, Kyung Peck, Andrei Holodny, Hrithwik Shalu **Published:** 2022-11-26T07:13:31Z **Abstract:** Whereas MRI produces anatomic information about the brain, functional MRI (fMRI) tells us about neural activity within the brain, including how various regions communicate with each other. The full chorus of conversations within the brain is summarized elegantly in the adjacency matrix. Although information-rich, adja...Votes: 0GitHub stars: 3
- Deep Rewiring Training Very Sparse Deep Networks**arXiv ID:** 1711.05136 **Authors:** Guillaume Bellec, David Kappel, Wolfgang Maass, Robert Legenstein **Published:** 2017-11-14T15:02:47Z **Abstract:** Neuromorphic hardware tends to pose limits on the connectivity of deep networks that one can run on them. But also generic hardware and software implementations of deep learning run more efficiently for sparse networks. Several methods exist for pruning connections of a neural network after it was trained without connectivity constraints. We...Votes: 0GitHub stars: 3
- Defense Against Llm Backdoors Using Critical NeuroSkill generated from arXiv paper 2607.19894: Defense Against LLM Backdoors using Critical Neuron Isolation PruningVotes: 0GitHub stars: 3
- Dendritic In Context Learning SnnDendriCL methodology for dendritic in-context learning in single-layer spiking neural networks. Shows that ICL requires neither attention, depth, nor inference-time plasticity: a single compartment with online-LMS dynamics is sufficient. Use when building SNNs with in-context learning capabilities, dendritic computation models, or biologically plausible learning mechanisms.Votes: 0GitHub stars: 3
- Diagnostic Method For Hydropower Plant Conditionbased Maintenance Combining Autoencoder With Clustering Algorithms**arXiv ID:** 2504.03649 **Authors:** Samy Jad, Xavier Desforges, Pierre-Yves Villard, Christian Caussidéry, Kamal Medjaher **Published:** 2025-02-24T08:57:47Z **Abstract:** The French company EDF uses supervisory control and data acquisition systems in conjunction with a data management platform to monitor hydropower plant, allowing engineers and technicians to analyse the time-series collected. Depending on the strategic importance of the monitored hydropower plant, the number of time-serie...Votes: 0GitHub stars: 3
- Diffusion Language Models For Speech Recognition**arXiv ID:** 2604.14001 **Authors:** Davyd Naveriani, Albert Zeyer, Ralf Schlüter, Hermann Ney **Published:** 2026-04-15T15:46:15Z **Abstract:** Diffusion language models have recently emerged as a leading alternative to standard language models, due to their ability for bidirectional attention and parallel text generation. In this work, we explore variants for their use in speech recognition. Specifically, we introduce a comprehensive guide to incorporating masked diffusion language models ...Votes: 0GitHub stars: 3
- Dmd High Frequency Eeg Brain DisorderDetecting high-frequency brain disorder signals using dynamic mode decomposition from EEG - methodology for extracting consistent and persistent dynamical changes in the high-frequency band from EEG signals of neurologically relevant channels, with applications in distinguishing alcohol-dependent groups from controls. Use when analyzing high-frequency EEG dynamics, brain disorder detection, or Dynamic Mode Decomposition applications in neuroscience.Votes: 0GitHub stars: 3
- Do Language Models Dream Of Binding Molecules BencDerived from arXiv:2607.18144 - Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial ConstraintsVotes: 0GitHub stars: 3
- Drawing Out Of Distribution With Neurosymbolic Generative Models**arXiv ID:** 2206.01829 **Authors:** Yichao Liang, Joshua B. Tenenbaum, Tuan Anh Le, N. Siddharth **Published:** 2022-06-03T21:40:22Z **Abstract:** Learning general-purpose representations from perceptual inputs is a hallmark of human intelligence. For example, people can write out numbers or characters, or even draw doodles, by characterizing these tasks as different instantiations of the same generic underlying process -- compositional arrangements of different forms of pen strokes. Crucia...Votes: 0GitHub stars: 3
- Dynamic Neural Manifolds ControlDynamic neural manifolds methodology for flexible closed-loop control on neuromorphic hardware. Uses sensory inputs to modulate heterogeneous inhibition, gain, and transient currents, driving rapid subspace rotations to switch between behaviors and fine-grained trajectory control within them.Votes: 0GitHub stars: 3
- Dynamic Neural Manifolds Neuromorphic ControlDynamic neural manifolds methodology for flexible closed-loop control on neuromorphic hardware. Uses ring attractor networks with sensory-modulated control neurons (speed, shape, selection) to drive subspace rotations and fine-grained trajectory control in neural state space. Implemented on SpiNNaker 2 chip with robotic maze navigation validation.Votes: 0GitHub stars: 3
- Dynamic Neural Manifolds NeuromorphicDynamic neural manifolds methodology for flexible closed-loop control on neuromorphic hardware. Implements low-dimensional manifold geometry on SpiNNaker 2 chip for real-time robotic control. Activation: neural manifolds, neuromorphic control, spiking networks, manifold geometry, SpiNNaker, closed-loop control, robotic navigationVotes: 0GitHub stars: 3
- Dynamic Neural Manifolds Snn ControlDynamic neural manifolds methodology for flexible closed-loop control on neuromorphic hardware. Spiking ring networks with control knobs (gain, inhibition, transient currents) that steer low-dimensional manifold geometry for explainable autonomous behavior. Implemented on SpiNNaker 2 chip. Activation: neural manifolds, neuromorphic control, SpiNNaker, ring network, subspace rotation, explainable SNN, closed-loop control, dynamic manifolds.Votes: 0GitHub stars: 3
- Dynamic Synaptic Lmg Quantum BrainBio-inspired quantum neural network using Lipkin-Meshkov-Glick (LMG) Hamiltonian with synaptic-efficacy feedback for activity-dependent homeostatic control. Use when: studying quantum brain models, quantum neural networks with homeostasis, LMG Hamiltonian for neural populations, collective quantum many-body attractors, quantum rhythmogenesis, population homeostasis in qubit systems, scalable quantum computational primitives.Votes: 0GitHub stars: 3
- Dynamical Alignment Snn Paradox ResolutionDynamical Alignment principle resolves SNN performance paradox. Fixed neural structure can operate in different computational modes driven by input temporal dynamics. Bimodal landscape: dissipative (energy-efficient sparse coding) vs expansive (high representational power). Timescale alignment between input and neuronal integration.Votes: 0GitHub stars: 3
- Dysco Latent Dynamics ExtractionDYSCO (Dynamics via Contrastive Learning) - Multi-view temporal contrastive learning for extracting governing equations from latent dynamics. Identifies dynamical systems from noisy high-dimensional observations with theoretical identifiability guarantees.Votes: 0GitHub stars: 3
- Eeg Based Lm EvaluationSkill for evaluating language models using EEG signals to examine human-like next-word prediction behavior based on arXiv:2607.16549. Enables fine-grained analysis of cognitive plausibility of language models during reading comprehension tasks.Votes: 0GitHub stars: 3
- Eeg Benchmarking Needs A Task Specification LayerDerived from arXiv:2606.22925 - EEG Benchmarking Needs a Task Specification Layer: NeuroDoc for Rulebook-Guided, Executable Benchmark ConstructionVotes: 0GitHub stars: 3
- Eeg Fm Stress Testing Clinical DecodingComprehensive benchmarking framework for stress-testing EEG foundation models with dataset identity analysis and targeted negative controls to evaluate clinical decoding robustness.Votes: 0GitHub stars: 3
- Eeg Fm Temporal Correlations BlindnessEEG foundation models lose long-range temporal correlations (LRTC) quantified by DFA exponent, showing spectral-temporal dissociation that causes cross-population fragility. Use when analyzing EEG foundation model limitations, temporal correlation preservation, or cross-population transfer issues.Votes: 0GitHub stars: 3
- Eeg Fuseformer Seizure PredictionTransformer-driven feature fusion framework for EEG-based seizure onset prediction. Combines CNN-LSTM (raw signal) + ResNet-18 (STFT) features via transformer encoder, achieves 98.85% recall on CHB-MIT dataset.Votes: 0GitHub stars: 3
- Emotion Recognition Of The Singing Voice Toward A Realtime Analysis Tool For Singers**arXiv ID:** 2105.00173 **Authors:** Daniel Szelogowski **Published:** 2021-05-01T05:47:15Z **Abstract:** Current computational-emotion research has focused on applying acoustic properties to analyze how emotions are perceived mathematically or used in natural language processing machine learning models. While recent interest has focused on analyzing emotions from the spoken voice, little experimentation has been performed to discover how emotions are recognized in the singing voice -- both ...Votes: 0GitHub stars: 3
- Enabling Efficient Processing Of Spiking Neural Networks With Onchip Learning On Commodity Neuromorphic Processors For Edge Ai Systems**arXiv ID:** 2504.00957 **Authors:** Rachmad Vidya Wicaksana Putra, Pasindu Wickramasinghe, Muhammad Shafique **Published:** 2025-04-01T16:52:03Z **Abstract:** The rising demand for energy-efficient edge AI systems (e.g., mobile agents/robots) has increased the interest in neuromorphic computing, since it offers ultra-low power/energy AI computation through spiking neural network (SNN) algorithms on neuromorphic processors. However, their efficient implementation strategy has not been compre...Votes: 0GitHub stars: 3
- Engram Memory Encoding And Retrieval A Neurocomputational Perspective**arXiv ID:** 2506.01659 **Authors:** Daniel Szelogowski **Published:** 2025-06-02T13:30:39Z **Abstract:** Despite substantial research into the biological basis of memory, the precise mechanisms by which experiences are encoded, stored, and retrieved in the brain remain incompletely understood. A growing body of evidence supports the engram theory, which posits that sparse populations of neurons undergo lasting physical and biochemical changes to support long-term memory. Yet, a comprehensiv...Votes: 0GitHub stars: 3
- Entangled Neural Trader Market StabilizationQuenching speculation in markets via entangled neural traders — prototype quantum stock market where entanglement between traders' valuations mitigates speculative busts before they emerge. RL agents with quantum-correlated qubit valuations learn to stabilize markets.Votes: 0GitHub stars: 3
- Entanglement Hyperlink RepresentationExact multipartite entanglement characterization using entanglement hyperlinks (EHLs) defined through the inclusion-exclusion principle.Votes: 0GitHub stars: 3
- Epileptic Seizure Detection In Separate Frequency Bands Using Feature Analysis And Graph Convolutional Neural Network Gcn From Electroencephalogram Eeg Signals**arXiv ID:** 2604.00163 **Authors:** Ferdaus Anam Jibon, Fazlul Hasan Siddiqui, F. Deeba, Gahangir Hossain **Published:** 2026-03-31T19:11:16Z **Abstract:** Epileptic seizures are neurological disorders characterized by abnormal and excessive electrical activity in the brain, resulting in recurrent seizure events. Electroencephalogram (EEG) signals are widely used for seizure diagnosis due to their ability to capture temporal and spatial neural dynamics. While recent deep learning methods ha...Votes: 0GitHub stars: 3
- Event Based Neural Decoding NeuroprostheticThis skill summarizes the methodology from arXiv:2607.11445v1 "Event-based Neural Decoding for Neuroprosthetic Motor Control". The paper proposes a high-performance neural decoding method that balances task performance and efficiency using an event-based gated recurrent unit (GRU) generating sparse communication with graded spikes, enabling on-device neural decoding for neuroprosthetics.Votes: 0GitHub stars: 3
- Evobrain Eeg Continual LearningEvoBrain 持续学习框架用于 EEG 基础模型跨任务统一解码。Neuro-Spectral Task Normalization (NSN) 处理分布和神经谱偏移，Response-Affinity Distillation (RAD) + 时间依赖回放缓解遗忘。在6个BCI任务上超越现有方法。Activation: EEG foundation model, continual learning, BCI, cross-task, neuro-spectral, distillation, 持续学习, 跨任务BCI, EEG基础模型.Votes: 0GitHub stars: 3
- Evoforest A Novel Machinelearning Paradigm Via Openended Evolution Of Computational Graphs**arXiv ID:** 2604.19761 **Authors:** Kamer Ali Yuksel, Hassan Sawaf **Published:** 2026-03-26T00:07:45Z **Abstract:** Modern machine learning is still largely organized around a single recipe: choose a parameterized model family and optimize its weights. Although highly successful, this paradigm is too narrow for many structured prediction problems, where the main bottleneck is not parameter fitting but discovering what should be computed from the data. Success often depends on identifying t...Votes: 0GitHub stars: 3