All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Global Workspace J SpaceAnthropic's discovery of emergent mental workspace (J-space) in Claude using Jacobian lens technique. Interpretability method for detecting hidden reasoning, misalignment, and enabling counterfactual reflection training for AI safety.Votes: 0GitHub stars: 3
- Graph Learningbased Regional Heavy Rainfall Prediction Using Lowcost Rain Gauges**arXiv ID:** 2412.16842 **Authors:** Edwin Salcedo **Published:** 2024-12-22T03:40:16Z **Abstract:** Accurate and timely prediction of heavy rainfall events is crucial for effective flood risk management and disaster preparedness. By monitoring, analysing, and evaluating rainfall data at a local level, it is not only possible to take effective actions to prevent any severe climate variation but also to improve the planning of surface and underground hydrological resources. However, developin...Votes: 0GitHub stars: 3
- Graph Memory Learning Imitating Lifelong Remembering And Forgetting Of Brain Networks**arXiv ID:** 2407.19183 **Authors:** Jiaxing Miao, Liang Hu, Qi Zhang, Longbing Cao **Published:** 2024-07-27T05:50:54Z **Abstract:** Graph data in real-world scenarios undergo rapid and frequent changes, making it challenging for existing graph models to effectively handle the continuous influx of new data and accommodate data withdrawal requests. The approach to frequently retraining graph models is resource intensive and impractical. To address this pressing challenge, this paper introduc...Votes: 0GitHub stars: 3
- Graphidyom Musical Expectation ModelingGraph-native Python reimplementation of the Information Dynamics of Music (IDyOM) model that represents predictive memories as explicit graph objects for musical expectation modeling and network analysis.Votes: 0GitHub stars: 3
- Grounded World Models In Biological Organisms And Future Embodied AiSkill for extracting and applying the grounded world modeling framework from biological organisms to inform future embodied AI systemsVotes: 0GitHub stars: 3
- Grounded World Models In Biological Organisms AndDerived from arXiv:2607.13560 - Grounded world models in biological organisms and future embodied AIVotes: 0GitHub stars: 3
- Guiding Inferences In Connection Tableau By Recurrent Neural Networks**arXiv ID:** 1905.07961 **Authors:** Bartosz Piotrowski, Josef Urban **Published:** 2019-05-20T09:47:41Z **Abstract:** We present a dataset and experiments on applying recurrent neural networks (RNNs) for guiding clause selection in the connection tableau proof calculus. The RNN encodes a sequence of literals from the current branch of the partial proof tree to a hidden vector state; using it, the system selects a clause for extending the proof tree. The training data and learning setup are ...Votes: 0GitHub stars: 3
- Hamilton Jacobi Reachability AnalysisUse for Hamilton-Jacobi reachability analysis and GRA tasks.Votes: 0GitHub stars: 3
- Hd 1sdi Qkd Steering**Source**: Monika Mothsara et al., "Robust One-Sided Device-Independent Quantum Key Distribution via High-Dimensional Steering" (arXiv:2607.08709, July 2026)Votes: 0GitHub stars: 3
- Heaviside Continuity Of Rolling Coefficients For EDerived from arXiv:2607.04562 - Heaviside Continuity of Rolling Coefficients for Eliminating Epistemic Entropy in Large Language ModelsVotes: 0GitHub stars: 3
- High Performance Im2win And Direct Convolutions Using Three Tensor Layouts On Simd Architectures**arXiv ID:** 2408.00278 **Authors:** Xiang Fu, Xinpeng Zhang, Jixiang Ma, Peng Zhao, Shuai Lu, Xu T. Liu **Published:** 2024-08-01T04:37:03Z **Abstract:** Convolution is the core component within deep neural networks and it is computationally intensive and time consuming. Tensor data layouts significantly impact convolution operations in terms of memory access and computational efficiency. Yet, there is still a lack of comprehensive performance characterization on data layouts on SIMD archit...Votes: 0GitHub stars: 3
- Hlbg Hyperbolic Learning Brain GraphsHyperbolic Learning on Brain Graphs (HLBG) methodology for brain network analysis using Lorentzian hyperbolic space to model hierarchical ROI-community-whole-brain relationships. Introduces Graph-aware Mamba (GaMamba) for capturing long-range dependencies while preserving graph topology. Achieves SOTA on ABIDE-I and REST-MDD disorder diagnosis. Activation: hyperbolic learning, brain graphs, functional connectivity, disorder diagnosis, Lorentzian space, graph mamba, hierarchical brain networks...Votes: 0GitHub stars: 3
- Homogeneous Artificial Neural Network**arXiv ID:** 2311.17973 **Authors:** Andrey Polyakov **Published:** 2023-11-29T16:16:32Z **Abstract:** The paper proposes an artificial neural network (ANN) being a global approximator for a special class of functions, which are known as generalized homogeneous. The homogeneity means a symmetry of a function with respect to a group of transformations having topological characterization of a dilation. In this paper, a class of the so-called linear dilations is considered. A homogeneous univer...Votes: 0GitHub stars: 3
- Hopfield Networks Dreaming TheoryStatistical-mechanical theory of dreaming in multidirectional associative memories using DLAM architecture. Use when: (1) implementing energy-based models with dreaming capabilities; (2) designing multi-layer Hebbian architectures; (3) analyzing pattern disentanglement in neural networks; (4) studying statistical mechanics of neural memory; (5) developing heteroassociative memory systems. Trigger words: Hopfield dreaming, DLAM, associative memory, energy-based models, pattern disentanglement.Votes: 0GitHub stars: 3
- How The Tensor Brain Uses Embeddings And Embodiment To Encode Senses And Symbols**arXiv ID:** 2409.12846 **Authors:** Volker Tresp, Hang Li **Published:** 2024-09-19T15:45:38Z **Abstract:** The Tensor Brain (TB) has been introduced as a computational model for perception and memory. This paper provides an overview of the TB model, incorporating recent developments and insights into its functionality. The TB is composed of two primary layers: the representation layer and the index layer. The representation layer serves as a model for the subsymbolic global workspace, a co...Votes: 0GitHub stars: 3
- Hybrid Activation Functions For Deep Neural Networks S3 And S4 A Novel Approach To Gradient Flow Optimization**arXiv ID:** 2507.22090 **Authors:** Sergii Kavun **Published:** 2025-07-29T09:21:57Z **Abstract:** Activation functions are critical components in deep neural networks, directly influencing gradient flow, training stability, and model performance. Traditional functions like ReLU suffer from dead neuron problems, while sigmoid and tanh exhibit vanishing gradient issues. We introduce two novel hybrid activation functions: S3 (Sigmoid-Softsign) and its improved version S4 (smoothed S3). S3 com...Votes: 0GitHub stars: 3
- Hyperbolic Learning Brain Graphs HlbgHyperbolic Learning on Brain Graphs (HLBG) methodology for brain disorder diagnosis using Lorentzian hyperbolic space and Graph-aware Mamba (GaMamba). Models hierarchical relationships among ROIs, functional communities, and whole-brain networks via geometric entailment constraints. Activation: hyperbolic brain graphs, brain network diagnosis, GaMamba, hyperbolic space brain, Lorentz model brain, hierarchical brain representation.Votes: 0GitHub stars: 3
- Ice StrategyICE StrategyVotes: 0GitHub stars: 3
- Icl Antibody AffinityIn-context learning methodology for antigen-specific antibody affinity ranking in computational immunologyVotes: 0GitHub stars: 3
- Illuminating The Space Of Beatable Lode Runner Levels Produced By Various Generative Adversarial Networks**arXiv ID:** 2101.07868 **Authors:** Kirby Steckel, Jacob Schrum **Published:** 2021-01-19T21:41:42Z **Abstract:** Generative Adversarial Networks (GANs) are capable of generating convincing imitations of elements from a training set, but the distribution of elements in the training set affects to difficulty of properly training the GAN and the quality of the outputs it produces. This paper looks at six different GANs trained on different subsets of data from the game Lode Runner. The qualit...Votes: 0GitHub stars: 3
- Im2win Memory Efficient Convolution On Simd Architectures**arXiv ID:** 2306.14320 **Authors:** Shuai Lu, Jun Chu, Xu T. Liu **Published:** 2023-06-25T19:21:10Z **Abstract:** Convolution is the most expensive operation among neural network operations, thus its performance is critical to the overall performance of neural networks. Commonly used convolution approaches, including general matrix multiplication (GEMM)-based convolution and direct convolution, rely on im2col for data transformation or do not use data transformation at all, respectively. H...Votes: 0GitHub stars: 3
- Image Captioning Using Deep Stacked Lstms Contextual Word Embeddings And Data Augmentation**arXiv ID:** 2102.11237 **Authors:** Sulabh Katiyar, Samir Kumar Borgohain **Published:** 2021-02-22T18:15:39Z **Abstract:** Image Captioning, or the automatic generation of descriptions for images, is one of the core problems in Computer Vision and has seen considerable progress using Deep Learning Techniques. We propose to use Inception-ResNet Convolutional Neural Network as encoder to extract features from images, Hierarchical Context based Word Embeddings for word representations and a D...Votes: 0GitHub stars: 3
- Improved Data Encoding For Emerging Computing Paradigms From Stochastic To Hyperdimensional Computing**arXiv ID:** 2501.02715 **Authors:** Mehran Shoushtari Moghadam, Sercan Aygun, M. Hassan Najafi **Published:** 2025-01-06T02:07:49Z **Abstract:** Data encoding is a fundamental step in emerging computing paradigms, particularly in stochastic computing (SC) and hyperdimensional computing (HDC), where it plays a crucial role in determining the overall system performance and hardware cost efficiency. This study presents an advanced encoding strategy that leverages a hardware-friendly class of l...Votes: 0GitHub stars: 3
- Improved Forecasting Using A Psordv Framework To Enhance Artificial Neural Network**arXiv ID:** 2402.18576 **Authors:** Sales Aribe **Published:** 2024-01-10T01:15:33Z **Abstract:** Decision making and planning have long relied heavily on AI-driven forecasts. The government and the general public are working to minimize the risks while maximizing benefits in the face of potential future public health uncertainties. This study used an improved method of forecasting utilizing the Random Descending Velocity Inertia Weight (RDV IW) technique to improve the convergence of Parti...Votes: 0GitHub stars: 3
- Improving The Performance Of Piecewise Linear Separation Incremental Algorithms For Practical Hardware Implementations**arXiv ID:** 0712.3654 **Authors:** Alejandro Chinea Manrique De Lara, Juan Manuel Moreno, Arostegui Jordi Madrenas, Joan Cabestany **Published:** 2007-12-21T10:05:52Z **Abstract:** In this paper we shall review the common problems associated with Piecewise Linear Separation incremental algorithms. This kind of neural models yield poor performances when dealing with some classification problems, due to the evolving schemes used to construct the resulting networks. So as to avoid this undesir...Votes: 0GitHub stars: 3
- Inclusion Of Domainknowledge Into Gnns Using Modedirected Inverse Entailment**arXiv ID:** 2105.10709 **Authors:** Tirtharaj Dash, Ashwin Srinivasan, A Baskar **Published:** 2021-05-22T12:25:13Z **Abstract:** We present a general technique for constructing Graph Neural Networks (GNNs) capable of using multi-relational domain knowledge. The technique is based on mode-directed inverse entailment (MDIE) developed in Inductive Logic Programming (ILP). Given a data instance $e$ and background knowledge $B$, MDIE identifies a most-specific logical formula $\bot_B(e)$ that c...Votes: 0GitHub stars: 3
- Inferscale Gpu Native Kv Injection For PersonalizeInferScale: GPU-Native KV Injection for Personalized LLM ServingVotes: 0GitHub stars: 3
- Information Coincidence IdentityInformation from coincidences — a single algebraic mixed coincidence identity that unifies information-theoretic variational results (Sanov, Chernoff, PAC-Bayes, Renyi). Use when deriving multi-prior information bounds, analyzing hypothesis testing error exponents, or building contrastive decoding frameworks.Votes: 0GitHub stars: 3
- Initialization Free Bernstein VaziraniInitialization-free Bernstein-Vazirani (IF-BV) algorithm methodology allowing arbitrary ancilla states as oracle register to improve probabilistic BV performance. Derives explicit formula for IF-BV performance, necessary and sufficient conditions for maximal performance, and proves IF-BV outperforms standard BV under suitable ordering assumptions on initial state coefficients. Activation: initialization-free BV algorithm, Bernstein-Vazirai ancilla state, probabilistic BV performance, quantum ...Votes: 0GitHub stars: 3
- Interpretation Learning And Empathy As One ConstraDerived from arXiv:2605.24999 - Interpretation, Learning, and Empathy as One Constraint: A Residual-Adequacy Architecture with Accountable AbstentionVotes: 0GitHub stars: 3
- Intrinsic Noise Consolidation DoobDoob-Barrier-Conditioned Diffusion methodology that turns analog neuromorphic device noise into a continual-learning resource. Casts per-synapse consolidation as a Doob h-transform, creating a noise-amplified restoring force that consolidates memories — predicting an inverted-U relationship between noise level and sequential-task retention.Votes: 0GitHub stars: 3
- Invariant Layers For Graphs With Nodes Of Different Types**arXiv ID:** 2302.13551 **Authors:** Dmitry Rybin, Ruoyu Sun, Zhi-Quan Luo **Published:** 2023-02-27T07:10:33Z **Abstract:** Neural networks that satisfy invariance with respect to input permutations have been widely studied in machine learning literature. However, in many applications, only a subset of all input permutations is of interest. For heterogeneous graph data, one can focus on permutations that preserve node types. We fully characterize linear layers invariant to such permutations...Votes: 0GitHub stars: 3
- Is Progressive Disclosure All You Need For Long CoDerived from arXiv:2607.17598 - Is Progressive Disclosure All You Need for Long-Context Agents?Votes: 0GitHub stars: 3
- Items Or Relations What Do Artificial Neural Networks Learn**arXiv ID:** 2404.12401 **Authors:** Renate Krause, Stefan Reimann **Published:** 2024-04-15T08:11:45Z **Abstract:** What has an Artificial Neural Network (ANN) learned after being successfully trained to solve a task - the set of training items or the relations between them? This question is difficult to answer for modern applied ANNs because of their enormous size and complexity. Therefore, here we consider a low-dimensional network and a simple task, i.e., the network has to reproduce a s...Votes: 0GitHub stars: 3
- Janus Foreseeing Latent Risk For Long Horizon AgenSkill generated from arXiv paper 2607.19913: JANUS: Foreseeing Latent Risk for Long-Horizon Agent SafetyVotes: 0GitHub stars: 3
- Kafnets Kernelbased Nonparametric Activation Functions For Neural Networks**arXiv ID:** 1707.04035 **Authors:** Simone Scardapane, Steven Van Vaerenbergh, Simone Totaro, Aurelio Uncini **Published:** 2017-07-13T09:22:01Z **Abstract:** Neural networks are generally built by interleaving (adaptable) linear layers with (fixed) nonlinear activation functions. To increase their flexibility, several authors have proposed methods for adapting the activation functions themselves, endowing them with varying degrees of flexibility. None of these approaches, however, have gai...Votes: 0GitHub stars: 3
- Kan Versus Mlp On Irregular Or Noisy Functions**arXiv ID:** 2408.07906 **Authors:** Chen Zeng, Jiahui Wang, Haoran Shen, Qiao Wang **Published:** 2024-08-15T03:24:07Z **Abstract:** In this paper, we compare the performance of Kolmogorov-Arnold Networks (KAN) and Multi-Layer Perceptron (MLP) networks on irregular or noisy functions. We control the number of parameters and the size of the training samples to ensure a fair comparison. For clarity, we categorize the functions into six types: regular functions, continuous functions with local...Votes: 0GitHub stars: 3
- Karushkuhntucker Conditiontrained Neural Networks Kkt Nets**arXiv ID:** 2410.15973 **Authors:** Shreya Arvind, Rishabh Pomaje, Rajshekhar V Bhat **Published:** 2024-10-21T12:59:58Z **Abstract:** This paper presents a novel approach to solving convex optimization problems by leveraging the fact that, under certain regularity conditions, any set of primal or dual variables satisfying the Karush-Kuhn-Tucker (KKT) conditions is necessary and sufficient for optimality. Similar to Theory-Trained Neural Networks (TTNNs), the parameters of the convex optimi...Votes: 0GitHub stars: 3
- Kernel Implicit Variational Inference**arXiv ID:** 1705.10119 **Authors:** Jiaxin Shi, Shengyang Sun, Jun Zhu **Published:** 2017-05-29T11:11:35Z **Abstract:** Recent progress in variational inference has paid much attention to the flexibility of variational posteriors. One promising direction is to use implicit distributions, i.e., distributions without tractable densities as the variational posterior. However, existing methods on implicit posteriors still face challenges of noisy estimation and computational infeasibility when...Votes: 0GitHub stars: 3
- Knowledge Centric Self ImprovementSkill generated from arXiv paper 2607.19592: Knowledge-Centric Self-ImprovementVotes: 0GitHub stars: 3
- Knowledgedriven Modulation Of Neural Networks With Attention Mechanism For Next Activity Prediction**arXiv ID:** 2312.08847 **Authors:** Ivan Donadello, Jonghyeon Ko, Fabrizio Maria Maggi, Jan Mendling, Francesco Riva, Matthias Weidlich **Published:** 2023-12-14T12:02:35Z **Abstract:** Predictive Process Monitoring (PPM) aims at leveraging historic process execution data to predict how ongoing executions will continue up to their completion. In recent years, PPM techniques for the prediction of the next activities have matured significantly, mainly thanks to the use of Neural Networks (NNs...Votes: 0GitHub stars: 3
- Kolmogorovarnold Networks For Metal Surface Defect Classification**arXiv ID:** 2501.06389 **Authors:** Maciej Krzywda, Mariusz Wermiński, Szymon Łukasik, Amir H. Gandomi **Published:** 2025-01-10T23:58:30Z **Abstract:** This paper presents the application of Kolmogorov-Arnold Networks (KAN) in classifying metal surface defects. Specifically, steel surfaces are analyzed to detect defects such as cracks, inclusions, patches, pitted surfaces, and scratches. Drawing on the Kolmogorov-Arnold theorem, KAN provides a novel approach compared to conventional multil...Votes: 0GitHub stars: 3
- Krein Space Riemann XiSpectral interpretation of the Riemann xi-function via Krein space quantization in de Sitter QFT. Uses invariant two-point functions, Legendre functions, Lorentzian harmonic analysis, and Mehler-Fock transform to construct a retarded propagator with xi-function spectral weight. Activation: Krein space quantization, Riemann xi-function spectral, de Sitter QFT, Legendre function, Mehler-Fock transform, Hilbert-Polya, critical line zerosVotes: 0GitHub stars: 3
- Krylov Lie Algebras VqaKrylov-Lie Algebras framework for Variational Quantum Algorithm (VQA) landscape analysis — provides numerically robust approximation of VQA reachable manifolds, weighted non-Haar variance formulas, and barren plateau mitigation via non-Haar corrections.Votes: 0GitHub stars: 3
- Landscape Of Neural Architecture Search Across Sensors How Much Do They Differ**arXiv ID:** 2201.06321 **Authors:** Kalifou René Traoré, Andrés Camero, Xiao Xiang Zhu **Published:** 2022-01-17T10:14:39Z **Abstract:** With the rapid rise of neural architecture search, the ability to understand its complexity from the perspective of a search algorithm is desirable. Recently, Traoré et al. have proposed the framework of Fitness Landscape Footprint to help describe and compare neural architecture search problems. It attempts at describing why a search strategy might be suc...Votes: 0GitHub stars: 3
- Large Language Models And Emergence A Complex Systems Perspective**arXiv ID:** 2506.11135 **Authors:** David C. Krakauer, John W. Krakauer, Melanie Mitchell **Published:** 2025-06-10T19:31:26Z **Abstract:** Emergence is a concept in complexity science that describes how many-body systems manifest novel higher-level properties, properties that can be described by replacing high-dimensional mechanisms with lower-dimensional effective variables and theories. This is captured by the idea "more is different". Intelligence is a consummate emergent property manif...Votes: 0GitHub stars: 3
- Latent Multitask Architecture Learning**arXiv ID:** 1705.08142 **Authors:** Sebastian Ruder, Joachim Bingel, Isabelle Augenstein, Anders Søgaard **Published:** 2017-05-23T08:58:09Z **Abstract:** Multi-task learning (MTL) allows deep neural networks to learn from related tasks by sharing parameters with other networks. In practice, however, MTL involves searching an enormous space of possible parameter sharing architectures to find (a) the layers or subspaces that benefit from sharing, (b) the appropriate amount of sharing, and (c...Votes: 0GitHub stars: 3
- Lattice Recurrent Unit Improving Convergence And Statistical Efficiency For Sequence Modeling**arXiv ID:** 1710.02254 **Authors:** Chaitanya Ahuja, Louis-Philippe Morency **Published:** 2017-10-06T01:52:14Z **Abstract:** Recurrent neural networks have shown remarkable success in modeling sequences. However low resource situations still adversely affect the generalizability of these models. We introduce a new family of models, called Lattice Recurrent Units (LRU), to address the challenge of learning deep multi-layer recurrent models with limited resources. LRU models achieve this goa...Votes: 0GitHub stars: 3
- Layerspecific Adaptive Learning Rates For Deep Networks**arXiv ID:** 1510.04609 **Authors:** Bharat Singh, Soham De, Yangmuzi Zhang, Thomas Goldstein, Gavin Taylor **Published:** 2015-10-15T16:31:46Z **Abstract:** The increasing complexity of deep learning architectures is resulting in training time requiring weeks or even months. This slow training is due in part to vanishing gradients, in which the gradients used by back-propagation are extremely large for weights connecting deep layers (layers near the output layer), and extremely small for sh...Votes: 0GitHub stars: 3
- Layup Asynchronous Decentralized Gradient Descent With Layerwise Updates**arXiv ID:** 2410.05985 **Authors:** Cabrel Teguemne Fokam, Marcel Nieveler, Lukas König, Khaleelulla Khan Nazeer, David Kappel, Anand Subramoney **Published:** 2024-10-08T12:32:36Z **Abstract:** The increasing size of deep learning models has made distributed training across multiple devices essential. Synchronous, centralized methods incur large communication and synchronization overheads. Communication efficient algorithms can reduce these overheads, but often require extra buffers, remai...Votes: 0GitHub stars: 3