All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Iqp Connectivity TrainabilityIQP circuit connectivity-trainability trade-off analysis methodology for near-term quantum optimization — systematic investigation of how circuit topology affects optimization performance and gradient behavior in Instantaneous Quantum Polynomial-time circuits.Votes: 0GitHub stars: 3
- Knowledge And Gradient Guided Reinforcement LearniKnowledge- and Gradient-Guided Reinforcement Learning for Parametrized Action Markov Decision Processes - In this paper, we study Reinforcement Learning in Parametrized Action Markov Decision Processes (PAMDP), where each decision consists of a symbolic ac...Votes: 0GitHub stars: 3
- Krylov Mean Field Chaos Predictability 2026 06 10Mean-field chaos 的预测性理论框架。证明随机循环网络的确定性混沌可通过连续历史唯一预测未来,展开功率谱到 Krylov 状态空间暴露潜在确定性组织。区分微观敏感性和预测复杂性。Votes: 0GitHub stars: 3
- Krylov Mean Field Chaos RnnKrylov Mean-Field Chaos in Random Recurrent Networks - Deterministic prediction theory for individual trajectories in mean-field dynamics. Analytic nonlinearities with fast Fourier decay expose latent determinism via Krylov state space hierarchy. Krylov growth rate sets prediction complexity and bounds largest Lyapunov exponent. Extends Hamiltonian chaotic dynamics ideas to classical dissipative systems. Activation: mean-field theory, Krylov chaos, RNN prediction, Lyapunov exponent, temporal ...Votes: 0GitHub stars: 3
- Language Models Dream Binding Molecules Benchmarking Llms Spatial ConstraintsSkill derived from arXiv:2607.18144 - Do Language Models Dream of Binding Molecules? Benchmarking LLMs under Spatial ConstraintsVotes: 0GitHub stars: 3
- Learn Like Humans Meta CognitiveLearn Like Humans - Meta-cognitive ReflectionVotes: 0GitHub stars: 3
- Learning Features And Their Transformations By Spatial And Temporal Spherical Clustering**arXiv ID:** 1308.2350 **Authors:** Jayanta K. Dutta, Bonny Banerjee **Published:** 2013-08-10T22:56:26Z **Abstract:** Learning features invariant to arbitrary transformations in the data is a requirement for any recognition system, biological or artificial. It is now widely accepted that simple cells in the primary visual cortex respond to features while the complex cells respond to features invariant to different transformations. We present a novel two-layered feedforward neural model that...Votes: 0GitHub stars: 3
- Learning Reasoning Strategies In Endtoend Differentiable Proving**arXiv ID:** 2007.06477 **Authors:** Pasquale Minervini, Sebastian Riedel, Pontus Stenetorp, Edward Grefenstette, Tim Rocktäschel **Published:** 2020-07-13T16:22:14Z **Abstract:** Attempts to render deep learning models interpretable, data-efficient, and robust have seen some success through hybridisation with rule-based systems, for example, in Neural Theorem Provers (NTPs). These neuro-symbolic models can induce interpretable rules and learn representations from data via back-propagation, ...Votes: 0GitHub stars: 3
- Learning To Walk Autonomously Via Resetfree Qualitydiversity**arXiv ID:** 2204.03655 **Authors:** Bryan Lim, Alexander Reichenbach, Antoine Cully **Published:** 2022-04-07T14:07:51Z **Abstract:** Quality-Diversity (QD) algorithms can discover large and complex behavioural repertoires consisting of both diverse and high-performing skills. However, the generation of behavioural repertoires has mainly been limited to simulation environments instead of real-world learning. This is because existing QD algorithms need large numbers of evaluations as well as...Votes: 0GitHub stars: 3
- Learning Under Noisy Supervision Is Governed By A Feedbacktruth Gap**arXiv ID:** 2602.16829 **Authors:** Elan Schonfeld, Elias Wisnia **Published:** 2026-02-18T19:50:56Z **Abstract:** When feedback is absorbed faster than task structure can be evaluated, the learner will favor feedback over truth. A two-timescale model shows this feedback-truth gap is inevitable whenever the two rates differ and vanishes only when they match. We test this prediction across neural networks trained with noisy labels (30 datasets, 2,700 runs), human probabilistic reversal learn...Votes: 0GitHub stars: 3
- Learning With Holographic Reduced Representations**arXiv ID:** 2109.02157 **Authors:** Ashwinkumar Ganesan, Hang Gao, Sunil Gandhi, Edward Raff, Tim Oates, James Holt, Mark McLean **Published:** 2021-09-05T19:37:34Z **Abstract:** Holographic Reduced Representations (HRR) are a method for performing symbolic AI on top of real-valued vectors by associating each vector with an abstract concept, and providing mathematical operations to manipulate vectors as if they were classic symbolic objects. This method has seen little use outside of older ...Votes: 0GitHub stars: 3
- Llm Enhanced Emotion Dynamics DecodingLLM-enhanced multi-target regression framework for decoding continuous emotion trajectories from brain fMRI using dynamic functional connectivityVotes: 0GitHub stars: 3
- Llms Can See The Smoke But Not The Fire EvaluatingLLMs Can See the Smoke but not the Fire: Evaluating Abductive Reasoning with Elenchos - Large language models (LLMs) excel at pattern recognition and text generation, but their capacity for abductive inference - inferring latent hypothese...Votes: 0GitHub stars: 3
- Longspike Fractional Order Snn State SpaceLongSpike fractional-order SSM for SNNs — enables efficient long-range dependency learning through fractional calculus while preserving sparse synaptic computationVotes: 0GitHub stars: 3
- Lottery Tickets In Evolutionary Optimization On Sparse Backpropagationfree Trainability**arXiv ID:** 2306.00045 **Authors:** Robert Tjarko Lange, Henning Sprekeler **Published:** 2023-05-31T15:58:54Z **Abstract:** Is the lottery ticket phenomenon an idiosyncrasy of gradient-based training or does it generalize to evolutionary optimization? In this paper we establish the existence of highly sparse trainable initializations for evolution strategies (ES) and characterize qualitative differences compared to gradient descent (GD)-based sparse training. We introduce a novel signal-to...Votes: 0GitHub stars: 3
- M3d Bfs Multimodal Brain Network FusionM3D-BFS - Multi-stage Dynamic Fusion Strategy for Sample-Adaptive Multimodal Brain Network Analysis. Proposes three fusion strategies (Weighted Sum, Gated Fusion, Cross-Attention) for integrating fMRI, DTI, and sMRI data with sample-wise attention mechanisms.Votes: 0GitHub stars: 3
- Maps Qudit VisualizationMulti-Axial Projective Sphere (MAPS) methodology for geometrically visualizing higher d-valued quantum state-space of qudits. Extends Bloch sphere to qudits with n projectional intersecting axes.Votes: 0GitHub stars: 3
- Masked Autoencoders Resting State Neural DataSelf-supervised pretraining on spontaneous neural activity using masked autoencoders to improve perception decoding in clinical neuroprosthetics. Achieves 84.1% accuracy on psychometric tasks and 64.0% on threshold-level tasks.Votes: 0GitHub stars: 3
- Maze Learning Using A Hyperdimensional Predictive Processing Cognitive Architecture**arXiv ID:** 2204.00619 **Authors:** Alexander Ororbia, M. Alex Kelly **Published:** 2022-03-31T04:44:28Z **Abstract:** We present the COGnitive Neural GENerative system (CogNGen), a cognitive architecture that combines two neurobiologically-plausible, computational models: predictive processing and hyperdimensional/vector-symbolic models. We draw inspiration from architectures such as ACT-R and Spaun/Nengo. CogNGen is in broad agreement with these, providing a level of detail between ACT-R'...Votes: 0GitHub stars: 3
- Memoryvla Temporal Modeling Robotic ManipulationMemoryVLA++ - Temporal modeling framework for VLA models with memory and imagination mechanisms for robotic manipulation. Includes working memory, perceptual-cognitive memory bank, world model for future state imagination, and diffusion action expert. Use for: long-horizon tasks, memory-dependent manipulation, temporal consistency, world prediction, robotic control.Votes: 0GitHub stars: 3
- Metabolic Quantum Limit MegMetabolic quantum limit methodology for magnetoencephalography (MEG) — combining quantum sensor energy resolution with neural metabolic power to derive fundamental information capacity bounds for brain imaging.Votes: 0GitHub stars: 3
- Metastable Mind Event SegmentationMetastable Mind framework synthesizing Event Segmentation (ES) and Metastable Neural Activity (MNA) theories. Neural states as fundamental computational units with spatio-temporally nested hierarchy, predictive models, and modular processing boundaries. Activation: metastable, event segmentation, neural states, cognitive segmentation, metastable neural activity, 亚稳态神经状态, 事件分割.Votes: 0GitHub stars: 3
- Mixed Potential Memristor Circuit ConvergenceMixed Potential approach for analyzing convergence of nonlinear RLC circuits with memristors using flux-charge analysis method (FCAM). Provides Lyapunov-like stability proofs for circuits with all four basic elements (resistors, inductors, capacitors, memristors). Applications: content addressable memories (CAMs), neuromorphic computing, nonlinear circuit stability analysis. Activation: memristor, circuit convergence, mixed potential, nonlinear RLC, flux-charge analysis, Lyapunov stability, c...Votes: 0GitHub stars: 3
- Mlxsnn Spiking Neural Networks On Apple Silicon Via Mlx**arXiv ID:** 2603.03529 **Authors:** Jiahao Qin **Published:** 2026-03-03T21:25:36Z **Abstract:** We introduce mlx-snn, the first spiking neural network (SNN) library built natively on Apple's MLX framework. As SNN research grows rapidly, all major libraries -- snnTorch, Norse, SpikingJelly, Lava -- target PyTorch or custom backends, leaving Apple Silicon users without a native option. mlx-snn provides six neuron models (LIF, IF, Izhikevich, Adaptive LIF, Synaptic, Alpha), four surrogate gra...Votes: 0GitHub stars: 3
- Modular Mechanistic Networks On Bridging Mechanistic And Phenomenological Models With Deep Neural Networks In Natural Language Processing**arXiv ID:** 1807.09844 **Authors:** Simon Dobnik, John D. Kelleher **Published:** 2018-07-21T11:37:15Z **Abstract:** Natural language processing (NLP) can be done using either top-down (theory driven) and bottom-up (data driven) approaches, which we call mechanistic and phenomenological respectively. The approaches are frequently considered to stand in opposition to each other. Examining some recent approaches in deep learning we argue that deep neural networks incorporate both perspectives...Votes: 0GitHub stars: 3
- Mohone Modeling Higher Order Network Effects In Knowledgegraphs Via Network Infused Embeddings**arXiv ID:** 1811.00198 **Authors:** Hao Yu, Vivek Kulkarni, William Wang **Published:** 2018-11-01T03:04:09Z **Abstract:** Many knowledge graph embedding methods operate on triples and are therefore implicitly limited by a very local view of the entire knowledge graph. We present a new framework MOHONE to effectively model higher order network effects in knowledge-graphs, thus enabling one to capture varying degrees of network connectivity (from the local to the global). Our framework is ge...Votes: 0GitHub stars: 3
- Moire Superlattice Synaptic MemorySecond-order synaptic memory methodology using moiré superlattice quantum materials — demonstrates intrinsic electronic hysteresis and plasticity in twisted double bilayer graphene (tDBLG) without extrinsic charge-traps, enabling pure-carbon quantum synaptic devices.Votes: 0GitHub stars: 3
- Mojo Ssl Neural DecodingMOJO (Masked autOencoder-based JOint training) framework for leveraging unlabelled neural data via self-supervised learning combined with supervised objectives. Enables robust neural population decoding with limited labelled data across species and modalities.Votes: 0GitHub stars: 3
- Mrine Multiscale Realtime Neural DecodingMultiscale Recurrent Inference Network for Encoding (MRINE) - real-time nonlinear latent factor modeling for multimodal neural activity decoding with different timescales and missing samplesVotes: 0GitHub stars: 3
- Multi Source Fmri TaskonomyMulti-source fMRI cognitive taskonomy framework using transfer learning for quantifying task relations. Extends single-source to multi-source transfer with masked reconstruction. Activation: fMRI taskonomy, cognitive task, transfer learning, brain encoding, task relation.Votes: 0GitHub stars: 3
- Multilingual Dialogue Act Recognition With Deep Learning Methods**arXiv ID:** 1904.05606 **Authors:** Jiří Martínek, Pavel Král, Ladislav Lenc, Christophe Cerisara **Published:** 2019-04-11T09:55:41Z **Abstract:** This paper deals with multi-lingual dialogue act (DA) recognition. The proposed approaches are based on deep neural networks and use word2vec embeddings for word representation. Two multi-lingual models are proposed for this task. The first approach uses one general model trained on the embeddings from all available languages. The second method ...Votes: 0GitHub stars: 3
- Multimodal Cognitive Maps Based On Neural Networks Trained On Successor Representations**arXiv ID:** 2401.01364 **Authors:** Paul Stoewer, Achim Schilling, Andreas Maier, Patrick Krauss **Published:** 2023-12-22T12:44:15Z **Abstract:** Cognitive maps are a proposed concept on how the brain efficiently organizes memories and retrieves context out of them. The entorhinal-hippocampal complex is heavily involved in episodic and relational memory processing, as well as spatial navigation and is thought to built cognitive maps via place and grid cells. To make use of the promising pr...Votes: 0GitHub stars: 3
- Multiscale Topology Optimization Using Neural Networks**arXiv ID:** 2404.08708 **Authors:** Hongrui Chen, Xingchen Liu, Levent Burak Kara **Published:** 2024-04-11T18:00:22Z **Abstract:** A long-standing challenge is designing multi-scale structures with good connectivity between cells while optimizing each cell to reach close to the theoretical performance limit. We propose a new method for direct multi-scale topology optimization using neural networks. Our approach focuses on inverse homogenization that seamlessly maintains compatibility acros...Votes: 0GitHub stars: 3
- Nanophotonet Pinn Inverse DesignPhysics-informed AI-driven inverse design framework for nonlinear metasurfaces using hybrid CNN-autoencoder architectureVotes: 0GitHub stars: 3
- Need Is All You Need Homeostatic Neural Networks Adapt To Concept Shift**arXiv ID:** 2205.08645 **Authors:** Kingson Man, Antonio Damasio, Hartmut Neven **Published:** 2022-05-17T21:49:16Z **Abstract:** In living organisms, homeostasis is the natural regulation of internal states aimed at maintaining conditions compatible with life. Typical artificial systems are not equipped with comparable regulatory features. Here, we introduce an artificial neural network that incorporates homeostatic features. Its own computing substrate is placed in a needful and vulnerabl...Votes: 0GitHub stars: 3
- Neocortical Plasticity An Unsupervised Cake But No Free Lunch**arXiv ID:** 1911.08584 **Authors:** Eilif B. Muller, Philippe Beaudoin **Published:** 2019-11-15T18:32:42Z **Abstract:** The fields of artificial intelligence and neuroscience have a long history of fertile bi-directional interactions. On the one hand, important inspiration for the development of artificial intelligence systems has come from the study of natural systems of intelligence, the mammalian neocortex in particular. On the other, important inspiration for models and theories of the...Votes: 0GitHub stars: 3
- Neural Architecture Search For Spiking Neural Networks**arXiv ID:** 2201.10355 **Authors:** Youngeun Kim, Yuhang Li, Hyoungseob Park, Yeshwanth Venkatesha, Priyadarshini Panda **Published:** 2022-01-23T16:34:27Z **Abstract:** Spiking Neural Networks (SNNs) have gained huge attention as a potential energy-efficient alternative to conventional Artificial Neural Networks (ANNs) due to their inherent high-sparsity activation. However, most prior SNN methods use ANN-like architectures (e.g., VGG-Net or ResNet), which could provide sub-optimal perform...Votes: 0GitHub stars: 3
- Neural Architecture Search With Mixed Bioinspired Learning Rules**arXiv ID:** 2507.13485 **Authors:** Imane Hamzaoui, Riyadh Baghdadi **Published:** 2025-07-17T18:49:38Z **Abstract:** Bio-inspired neural networks are attractive for their adversarial robustness, energy frugality, and closer alignment with cortical physiology, yet they often lag behind back-propagation (BP) based models in accuracy and ability to scale. We show that allowing the use of different bio-inspired learning rules in different layers, discovered automatically by a tailored neural-a...Votes: 0GitHub stars: 3
- Neural Decoder Confidence QecGraph neural network decoder confidence as learned proxy for logical gap in quantum error correction. The logit of a pretrained GNN decoder acts as a reliable proxy for minimum-weight perfect matching (MWPM) logical gap, enabling soft-information error correction without the computational overhead. Use when designing QEC decoders, implementing soft-decision quantum error correction, or evaluating decoder reliability.Votes: 0GitHub stars: 3
- Neural Model Reprogramming With Similarity Based Mapping For Lowresource Spoken Command Recognition**arXiv ID:** 2110.03894 **Authors:** Hao Yen, Pin-Jui Ku, Chao-Han Huck Yang, Hu Hu, Sabato Marco Siniscalchi, Pin-Yu Chen, Yu Tsao **Published:** 2021-10-08T05:07:35Z **Abstract:** In this study, we propose a novel adversarial reprogramming (AR) approach for low-resource spoken command recognition (SCR), and build an AR-SCR system. The AR procedure aims to modify the acoustic signals (from the target domain) to repurpose a pretrained SCR model (from the source domain). To solve the label mi...Votes: 0GitHub stars: 3
- Neural Quantum State EncodingQuantum state preparation via neural network encoding methodology. Maps classical data to quantum circuit parameters using a trained neural network, avoiding iterative variational optimization for each data instance. Achieves high-fidelity state preparation (up to 0.992) with 5000x speedup over per-instance optimization. Use when designing quantum machine learning pipelines that need efficient data loading, amplitude encoding, or scalable quantum state preparation on NISQ devices. Applies to ...Votes: 0GitHub stars: 3
- Neural Quantum State Vqmc CorrelatedNeural network quantum state (NQS) variational Monte Carlo for correlated superconducting nanostructures. Maps quantum dot clusters to particle-number-conserving representations for fermionic NQS-VMC treatment. Identifies trivial singlet, strongly correlated Heisenberg, and critical intermediate regimes. 1D singlet-doublet transitions, 2D robust triplet ground states. Use when studying correlated superconducting systems, quantum dot arrays, or fermionic neural quantum states.Votes: 0GitHub stars: 3
- Neural Sentinel Unified Vision Language Model Vlm For License Plate Recognition With Humanintheloop Continual Learning**arXiv ID:** 2602.07051 **Authors:** Karthik Sivakoti **Published:** 2026-02-04T16:04:15Z **Abstract:** Traditional Automatic License Plate Recognition (ALPR) systems employ multi-stage pipelines consisting of object detection networks followed by separate Optical Character Recognition (OCR) modules, introducing compounding errors, increased latency, and architectural complexity. This research presents Neural Sentinel, a novel unified approach that leverages Vision Language Models (VLMs) to ...Votes: 0GitHub stars: 3
- Neural Transfer Unification QecNeural Transfer Unification (NTU) framework for efficient foundation decoders in fault-tolerant quantum computing at large code distancesVotes: 0GitHub stars: 3
- Neural Transfer UnificationNeural Transfer Unification (NTU) methodology for efficient foundation decoders in fault-tolerant quantum computing. Aligns decoding tasks across code distances via shared algebraic structures, enabling knowledge transfer from small to large code distances. Use when designing quantum error correction decoders, neural decoders for surface codes, or cross-distance knowledge transfer for quantum fault tolerance. Triggers: quantum decoder, foundation decoder, neural transfer, code distance scalin...Votes: 0GitHub stars: 3
- Neuro Inspired Inverse LearningNeuro-inspired Inverse Learning framework for planning and control — bridges RL amortization and optimal control with quantum gate applicationsVotes: 0GitHub stars: 3
- Neuro Quantum ResearchResearch methodology for the intersection of neuroscience and quantum physics/computing. Use when analyzing papers or research at the boundary of brain science and quantum mechanics, including quantum neural networks, quantum memory models of cognition, quantum-inspired brain simulation, quantum computing for neuroscience, and quantum effects in biological systems. Triggers: quantum neuroscience, quantum brain, quantum neural network, quantum memory, quantum cognition, neuromorphic quantum, q...Votes: 0GitHub stars: 3
- Neuromorphic Spiking Ring Attractor V2Neuromorphic spiking ring-attractor network for proprioceptive joint-state estimation on Intel Loihi. Implements continuous attractor dynamics with recurrent E/I populations for stable encoding of continuous variables. Low-power robotic control with biological plausibility. Activation: spiking ring attractor, proprioceptive estimation, Loihi neuromorphic, continuous attractor, joint-state encoding.Votes: 0GitHub stars: 3
- Neuromorphic Supremacy Hybrid Astrocytic SpikingNeuromorphic Supremacy methodology for hybrid neural architectures combining astrocytic modulation and spiking dynamics with conventional ANNs. Enables few-shot learning and robust performance under severe noise (occlusion, impulse noise). Use when building embodied AI systems for data-scarce noisy environments, designing neuromorphic circuits, or implementing hybrid biological-artificial architectures. Keywords: neuromorphic supremacy, astrocyte, spiking neural network, few-shot learning, no...Votes: 0GitHub stars: 3
- Neuronav A Library For Neurallyplausible Reinforcement Learning**arXiv ID:** 2206.03312 **Authors:** Arthur Juliani, Samuel Barnett, Brandon Davis, Margaret Sereno, Ida Momennejad **Published:** 2022-06-06T16:33:36Z **Abstract:** In this work we propose Neuro-Nav, an open-source library for neurally plausible reinforcement learning (RL). RL is among the most common modeling frameworks for studying decision making, learning, and navigation in biological organisms. In utilizing RL, cognitive scientists often handcraft environments and agents to meet the ne...Votes: 0GitHub stars: 3