All authors
Claude Skills by hiyenwong
github.com/hiyenwong9,934 skills5 installs19,223 views
- Le Critique Privileged Value FunctionsPrivileged Value Functions for LLM reinforcement learning.Votes: 0GitHub stars: 3
- Leact Learning To Reason From Expert ActionsLeAct framework for recovering chain-of-thought reasoning from expert systems that only produce actions without explicit reasoning traces, treating CoT as a latent variable optimized via action probability scoring.Votes: 0GitHub stars: 3
- Learn To Bind And Grow Neural Structures**arXiv ID:** 2011.10568 **Authors:** Azhar Shaikh, Nishant Sinha **Published:** 2020-11-21T09:40:26Z **Abstract:** Task-incremental learning involves the challenging problem of learning new tasks continually, without forgetting past knowledge. Many approaches address the problem by expanding the structure of a shared neural network as tasks arrive, but struggle to grow optimally, without losing past knowledge. We present a new framework, Learn to Bind and Grow, which learns a neural architec...Votes: 0GitHub stars: 3
- Learning By Active Forgetting For Neural Networks**arXiv ID:** 2111.10831 **Authors:** Jian Peng, Xian Sun, Min Deng, Chao Tao, Bo Tang, Wenbo Li, Guohua Wu, QingZhu, Yu Liu, Tao Lin, Haifeng Li **Published:** 2021-11-21T14:55:03Z **Abstract:** Remembering and forgetting mechanisms are two sides of the same coin in a human learning-memory system. Inspired by human brain memory mechanisms, modern machine learning systems have been working to endow machine with lifelong learning capability through better remembering while pushing the forgett...Votes: 0GitHub stars: 3
- Learning Conjecturing From Scratch**arXiv ID:** 2503.01389 **Authors:** Thibault Gauthier, Josef Urban **Published:** 2025-03-03T10:39:38Z **Abstract:** We develop a self-learning approach for conjecturing of induction predicates on a dataset of 16197 problems derived from the OEIS. These problems are hard for today's SMT and ATP systems because they require a combination of inductive and arithmetical reasoning. Starting from scratch, our approach consists of a feedback loop that iterates between (i) training a neural transla...Votes: 0GitHub stars: 3
- Learning Optimal And Nearoptimal Lexicographic Preference Lists**arXiv ID:** 1909.09072 **Authors:** Ahmed Moussa, Xudong Liu **Published:** 2019-09-19T16:10:46Z **Abstract:** We consider learning problems of an intuitive and concise preference model, called lexicographic preference lists (LP-lists). Given a set of examples that are pairwise ordinal preferences over a universe of objects built of attributes of discrete values, we want to learn (1) an optimal LP-list that decides the maximum number of these examples, or (2) a near-optimal LP-list that dec...Votes: 0GitHub stars: 3
- Learning Plannable Representations With Causal Infogan**arXiv ID:** 1807.09341 **Authors:** Thanard Kurutach, Aviv Tamar, Ge Yang, Stuart Russell, Pieter Abbeel **Published:** 2018-07-24T20:46:05Z **Abstract:** In recent years, deep generative models have been shown to 'imagine' convincing high-dimensional observations such as images, audio, and even video, learning directly from raw data. In this work, we ask how to imagine goal-directed visual plans -- a plausible sequence of observations that transition a dynamical system from its current con...Votes: 0GitHub stars: 3
- Learning Successor Features With Distributed Hebbian Temporal Memory**arXiv ID:** 2310.13391 **Authors:** Evgenii Dzhivelikian, Petr Kuderov, Aleksandr I. Panov **Published:** 2023-10-20T10:03:14Z **Abstract:** This paper presents a novel approach to address the challenge of online sequence learning for decision making under uncertainty in non-stationary, partially observable environments. The proposed algorithm, Distributed Hebbian Temporal Memory (DHTM), is based on the factor graph formalism and a multi-component neuron model. DHTM aims to capture sequenti...Votes: 0GitHub stars: 3
- Learning Theorem Proving Components**arXiv ID:** 2107.10034 **Authors:** Karel Chvalovský, Jan Jakubův, Miroslav Olšák, Josef Urban **Published:** 2021-07-21T12:00:05Z **Abstract:** Saturation-style automated theorem provers (ATPs) based on the given clause procedure are today the strongest general reasoners for classical first-order logic. The clause selection heuristics in such systems are, however, often evaluating clauses in isolation, ignoring other clauses. This has changed recently by equipping the E/ENIGMA system with ...Votes: 0GitHub stars: 3
- Learning To Control Selfassembling Morphologies A Study Of Generalization Via Modularity**arXiv ID:** 1902.05546 **Authors:** Deepak Pathak, Chris Lu, Trevor Darrell, Phillip Isola, Alexei A. Efros **Published:** 2019-02-14T18:59:05Z **Abstract:** Contemporary sensorimotor learning approaches typically start with an existing complex agent (e.g., a robotic arm), which they learn to control. In contrast, this paper investigates a modular co-evolution strategy: a collection of primitive agents learns to dynamically self-assemble into composite bodies while also learning to coordina...Votes: 0GitHub stars: 3
- Learning To Execute**arXiv ID:** 1410.4615 **Authors:** Wojciech Zaremba, Ilya Sutskever **Published:** 2014-10-17T01:35:12Z **Abstract:** Recurrent Neural Networks (RNNs) with Long Short-Term Memory units (LSTM) are widely used because they are expressive and are easy to train. Our interest lies in empirically evaluating the expressiveness and the learnability of LSTMs in the sequence-to-sequence regime by training them to evaluate short computer programs, a domain that has traditionally been seen as too compl...Votes: 0GitHub stars: 3
- Learning To Program Quantum Measurements For Machine Learning**arXiv ID:** 2505.13525 **Authors:** Samuel Yen-Chi Chen, Huan-Hsin Tseng, Hsin-Yi Lin, Shinjae Yoo **Published:** 2025-05-18T02:39:22Z **Abstract:** The rapid advancements in quantum computing (QC) and machine learning (ML) have sparked significant interest, driving extensive exploration of quantum machine learning (QML) algorithms to address a wide range of complex challenges. The development of high-performance QML models requires expert-level expertise, presenting a key challenge to the ...Votes: 0GitHub stars: 3
- Learning With Molecules Beyond Graph Neural Networks**arXiv ID:** 2011.03488 **Authors:** Gustav Sourek, Filip Zelezny, Ondrej Kuzelka **Published:** 2020-11-06T17:42:42Z **Abstract:** We demonstrate a deep learning framework which is inherently based in the highly expressive language of relational logic, enabling to, among other things, capture arbitrarily complex graph structures. We show how Graph Neural Networks and similar models can be easily covered in the framework by specifying the underlying propagation rules in the relational logic....Votes: 0GitHub stars: 3
- Lightweight Neural Networks**arXiv ID:** 1712.05695 **Authors:** Altaf H. Khan **Published:** 2017-12-15T14:56:05Z **Abstract:** Most of the weights in a Lightweight Neural Network have a value of zero, while the remaining ones are either +1 or -1. These universal approximators require approximately 1.1 bits/weight of storage, posses a quick forward pass and achieve classification accuracies similar to conventional continuous-weight networks. Their training regimen focuses on error reduction initially, but later emphas...Votes: 0GitHub stars: 3
- Llmet Enabling Cross Layer Evaluation Of EmergingLLMET: Enabling Cross-Layer Evaluation of Emerging M3D Memories for Energy-Efficient LLM ServingVotes: 0GitHub stars: 3
- Local Synaptic Rules Sigreg GradientLocal synaptic learning rules (STDP+ and homeostatic plasticity) can implement exact SIGReg-like self-supervised learning gradients without backpropagation, global error signals, or weight transport.Votes: 0GitHub stars: 3
- Localizing Catastrophic Forgetting In Neural Networks**arXiv ID:** 1906.02568 **Authors:** Felix Wiewel, Bin Yang **Published:** 2019-06-06T13:18:03Z **Abstract:** Artificial neural networks (ANNs) suffer from catastrophic forgetting when trained on a sequence of tasks. While this phenomenon was studied in the past, there is only very limited recent research on this phenomenon. We propose a method for determining the contribution of individual parameters in an ANN to catastrophic forgetting. The method is used to analyze an ANNs response to thr...Votes: 0GitHub stars: 3
- Logic Explained Networks**arXiv ID:** 2108.05149 **Authors:** Gabriele Ciravegna, Pietro Barbiero, Francesco Giannini, Marco Gori, Pietro Lió, Marco Maggini, Stefano Melacci **Published:** 2021-08-11T10:55:42Z **Abstract:** The large and still increasing popularity of deep learning clashes with a major limit of neural network architectures, that consists in their lack of capability in providing human-understandable motivations of their decisions. In situations in which the machine is expected to support the decision...Votes: 0GitHub stars: 3
- Lonic Algorithm Hardware CodesignLonic: INT4 algorithm-hardware co-design for SNNs.Votes: 0GitHub stars: 3
- Low Depth Nonmarkovian SimulationLow-depth quantum simulation of non-Markovian dynamics using trajectory mixing — trades entangling gates for statistical mixture of independent pure state trajectories to reduce circuit depth on NISQ hardware. Activation: non-Markovian simulation, trajectory mixing, low-depth quantum simulation, memory channel simulation, mixed unitary channels, near-term quantum hardware.Votes: 0GitHub stars: 3
- Machine Learning Classification Of Nonmarkovian Noise Disturbing Quantum Dynamics**arXiv ID:** 2101.03221 **Authors:** Stefano Martina, Stefano Gherardini, Filippo Caruso **Published:** 2021-01-08T20:56:56Z **Abstract:** In this paper machine learning and artificial neural network models are proposed for the classification of external noise sources affecting a given quantum dynamics. For this purpose, we train and then validate support vector machine, multi-layer perceptron and recurrent neural network models with different complexity and accuracy, to solve supervised bin...Votes: 0GitHub stars: 3
- Machine Unlearning Using Forgetting Neural Networks**arXiv ID:** 2410.22374 **Authors:** Amartya Hatua, Trung T. Nguyen, Filip Cano, Andrew H. Sung **Published:** 2024-10-29T02:52:26Z **Abstract:** Modern computer systems store vast amounts of personal data, enabling advances in AI and ML but risking user privacy and trust. For privacy reasons, it is sometimes desired for an ML model to forget part of the data it was trained on. In this paper, we introduce a novel unlearning approach based on Forgetting Neural Networks (FNNs), a neuroscience-...Votes: 0GitHub stars: 3
- Manifold Mixup Better Representations By Interpolating Hidden States**arXiv ID:** 1806.05236 **Authors:** Vikas Verma, Alex Lamb, Christopher Beckham, Amir Najafi, Ioannis Mitliagkas, Aaron Courville, David Lopez-Paz, Yoshua Bengio **Published:** 2018-06-13T19:32:59Z **Abstract:** Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples. This includes distribution shifts, outliers, and adversarial examples. To address these issues, we propose Manifold Mix...Votes: 0GitHub stars: 3
- Mean Field Oscillatory Low Rank RnnMean-field theory for rich oscillatory dynamics in low-rank recurrent networks with activity-dependent adaptation. Analyzes how low-rank structure and adaptation interact to produce complex oscillatory and chaotic behavior in recurrent neural networks.Votes: 0GitHub stars: 3
- Measurement Incompatibility RandomnessQuantum randomness certification framework using measurement incompatibility witnesses — bounds classical eavesdropper capabilities via semi-definite programming using generalised robustness as a geometric incompatibility measure. Use when certifying quantum random number generators, analyzing prepare-and-measure security, or quantifying the randomness-geometric incompatibility trade-off.Votes: 0GitHub stars: 3
- Memory Networks Towards Fully Biologically Plausible Learning**arXiv ID:** 2409.17282 **Authors:** Jacobo Ruiz, Manas Gupta **Published:** 2024-09-18T06:01:35Z **Abstract:** The field of artificial intelligence faces significant challenges in achieving both biological plausibility and computational efficiency, particularly in visual learning tasks. Current artificial neural networks, such as convolutional neural networks, rely on techniques like backpropagation and weight sharing, which do not align with the brain's natural information processing metho...Votes: 0GitHub stars: 3
- Meta Continual Learning**arXiv ID:** 1806.06928 **Authors:** Risto Vuorio, Dong-Yeon Cho, Daejoong Kim, Jiwon Kim **Published:** 2018-06-11T06:49:54Z **Abstract:** Using neural networks in practical settings would benefit from the ability of the networks to learn new tasks throughout their lifetimes without forgetting the previous tasks. This ability is limited in the current deep neural networks by a problem called catastrophic forgetting, where training on new tasks tends to severely degrade performance on previo...Votes: 0GitHub stars: 3
- Metis Memory Foundation ModelMetis: Memory Foundation ModelVotes: 0GitHub stars: 3
- Mlref Module Reward Evolution FrameworkMLREF (Module Level Reward Evolution Framework) for efficient module reuse in reinforcement learning reward design via large language models. Use when designing reward functions for RL that need to evolve across iterations while preserving and reusing effective components.Votes: 0GitHub stars: 3
- Monroe Molecular Foundation ModelMonroe molecular foundation model for in-context probabilistic inference using prior-data-fitted models (TabPFN). Use when performing bioassay activity prediction with data-limited scenarios requiring general-purpose chemical knowledge.Votes: 0GitHub stars: 3
- Motion Planning Of An Autonomous Mobile Robot Using Artificial Neural Network**arXiv ID:** 1207.4931 **Authors:** G. N. Tripathi, V. Rihani **Published:** 2012-07-20T12:15:12Z **Abstract:** The paper presents the electronic design and motion planning of a robot based on decision making regarding its straight motion and precise turn using Artificial Neural Network (ANN). The ANN helps in learning of robot so that it performs motion autonomously. The weights calculated are implemented in microcontroller. The performance has been tested to be excellent.Votes: 0GitHub stars: 3
- Multi Expression Programming An Indepth Description**arXiv ID:** 2110.00367 **Authors:** Mihai Oltean **Published:** 2021-09-29T01:57:18Z **Abstract:** Multi Expression Programming (MEP) is a Genetic Programming variant that uses a linear representation of chromosomes. MEP individuals are strings of genes encoding complex computer programs. When MEP individuals encode expressions, their representation is similar to the way in which compilers translate $C$ or $Pascal$ expressions into machine code. A unique MEP feature is the ability to store ...Votes: 0GitHub stars: 3
- Multilabel Classification Method Based On Extreme Learning Machines**arXiv ID:** 1608.08435 **Authors:** Rajasekar Venkatesan, Meng Joo Er **Published:** 2016-08-30T13:08:06Z **Abstract:** In this paper, an Extreme Learning Machine (ELM) based technique for Multi-label classification problems is proposed and discussed. In multi-label classification, each of the input data samples belongs to one or more than one class labels. The traditional binary and multi-class classification problems are the subset of the multi-label problem with the number of labels corr...Votes: 0GitHub stars: 3
- Multiobjective Qualitydiversity For Crystal Structure Prediction**arXiv ID:** 2403.17164 **Authors:** Hannah Janmohamed, Marta Wolinska, Shikha Surana, Thomas Pierrot, Aron Walsh, Antoine Cully **Published:** 2024-03-25T20:29:04Z **Abstract:** Crystal structures are indispensable across various domains, from batteries to solar cells, and extensive research has been dedicated to predicting their properties based on their atomic configurations. However, prevailing Crystal Structure Prediction methods focus on identifying the most stable solutions that lie a...Votes: 0GitHub stars: 3
- Multitask Learning On Networks**arXiv ID:** 2112.04891 **Authors:** Andrea Ponti **Published:** 2021-12-07T09:13:10Z **Abstract:** The multi-task learning (MTL) paradigm can be traced back to an early paper of Caruana (1997) in which it was argued that data from multiple tasks can be used with the aim to obtain a better performance over learning each task independently. A solution of MTL with conflicting objectives requires modelling the trade-off among them which is generally beyond what a straight linear combination can...Votes: 0GitHub stars: 3
- Multivariate Time Series Anomaly Detection With Few Positive Samples**arXiv ID:** 2207.00705 **Authors:** Feng Xue, Weizhong Yan **Published:** 2022-07-02T00:58:52Z **Abstract:** Given the scarcity of anomalies in real-world applications, the majority of literature has been focusing on modeling normality. The learned representations enable anomaly detection as the normality model is trained to capture certain key underlying data regularities under normal circumstances. In practical settings, particularly industrial time series anomaly detection, we often enco...Votes: 0GitHub stars: 3
- Nahid Aibased Algorithm For Operating Fullyautomatic Surgery**arXiv ID:** 2401.08584 **Authors:** Sina Saadati **Published:** 2023-11-03T12:35:07Z **Abstract:** In this paper, for the first time, a method is presented that can provide a fully automated surgery based on software and computer vision techniques. Then, the advantages and challenges of computerization of medical surgery are examined. Finally, the surgery related to isolated ovarian endometriosis disease has been examined, and based on the presented method, a more detailed algorithm is pres...Votes: 0GitHub stars: 3
- Neural Allocentric Intuitive Physics Prediction From Real Videos**arXiv ID:** 1809.03330 **Authors:** Zhihua Wang, Stefano Rosa, Yishu Miao, Zihang Lai, Linhai Xie, Andrew Markham, Niki Trigoni **Published:** 2018-09-07T10:33:56Z **Abstract:** Humans are able to make rich predictions about the future dynamics of physical objects from a glance. On the other hand, most existing computer vision approaches require strong assumptions about the underlying system, ad-hoc modeling, or annotated datasets, to carry out even simple predictions. To tackle this gap, w...Votes: 0GitHub stars: 3
- Neural Cellular Automata AttractorsNeural Cellular Automata (NCA) attractor analysis methodology. Studies stability, geometry, and dynamics of learned attractors in self-organizing neural systems using dynamical systems theory. Methods for analyzing ordered vs chaotic behavior, long-horizon stability estimation, and perturbation responses in NCA. Activation: NCA attractor, neural cellular automata, self-organizing neural, attractor stability, dynamical systems NCA.Votes: 0GitHub stars: 3
- Neural Constraint Satisfaction Hierarchical Abstraction For Combinatorial Generalization In Object Rearrangement**arXiv ID:** 2303.11373 **Authors:** Michael Chang, Alyssa L. Dayan, Franziska Meier, Thomas L. Griffiths, Sergey Levine, Amy Zhang **Published:** 2023-03-20T18:19:36Z **Abstract:** Object rearrangement is a challenge for embodied agents because solving these tasks requires generalizing across a combinatorially large set of configurations of entities and their locations. Worse, the representations of these entities are unknown and must be inferred from sensory percepts. We present a hierarch...Votes: 0GitHub stars: 3
- Neural Inverse Design Srf CavityDeep neural network approaches for inverse design of superconducting radio-frequency (SRF) cavities and transmon qubits for bosonic quantum computation — mapping target device parameters to candidate geometries.Votes: 0GitHub stars: 3
- Neuroncentric Hebbian Learning**arXiv ID:** 2403.12076 **Authors:** Andrea Ferigo, Elia Cunegatti, Giovanni Iacca **Published:** 2024-02-16T17:38:28Z **Abstract:** One of the most striking capabilities behind the learning mechanisms of the brain is the adaptation, through structural and functional plasticity, of its synapses. While synapses have the fundamental role of transmitting information across the brain, several studies show that it is the neuron activations that produce changes on synapses. Yet, most plasticity mo...Votes: 0GitHub stars: 3
- Neuroscience 2607 12403Skill for applying the methods from the arXiv paper: Structured Fluctuations and the Information Dynamics of Self-Maintenance in Growing Neural Cellular Automata (arXiv:2607.12403). This skill provides a framework for analyzing internal fluctuations in neural cellular automata as a functional component for self-maintenance and self-repair.Votes: 0GitHub stars: 3
- Neurosymbolic Ai And Its Taxonomy A Survey**arXiv ID:** 2305.08876 **Authors:** Wandemberg Gibaut, Leonardo Pereira, Fabio Grassiotto, Alexandre Osorio, Eder Gadioli, Amparo Munoz, Sildolfo Gomes, Claudio dos Santos **Published:** 2023-05-12T19:51:13Z **Abstract:** Neurosymbolic AI deals with models that combine symbolic processing, like classic AI, and neural networks, as it's a very established area. These models are emerging as an effort toward Artificial General Intelligence (AGI) by both exploring an alternative to just increasi...Votes: 0GitHub stars: 3
- New Feature For Complex Network Based On Ant Colony Optimization For High Level Classification**arXiv ID:** 2008.12884 **Authors:** Josimar E. Chire-Saire **Published:** 2020-08-29T00:22:43Z **Abstract:** Low level classification extracts features from the elements, i.e. physical to use them to train a model for a later classification. High level classification uses high level features, the existent patterns, relationship between the data and combines low and high level features for classification. High Level features can be got from Complex Network created over the data. Local and gl...Votes: 0GitHub stars: 3
- Noisy Group Neurons Synchronous ResettingNoisy Group Neurons (NGN) framework for high-performance spiking neural networks using population-level synchronous resetting and neural stochasticity. Combines NGN model with backpropagation learning based on mean-field dynamics to address spatiotemporal information loss and gradient mismatching in deep SNNs. Use when implementing or analyzing SNNs with stochastic resonance, synchronous resetting, or mean-field learning approaches.Votes: 0GitHub stars: 3
- Non Hermitian Conscious Preconscious SubliminalNon-Hermitian Potential Well Formalism for modeling conscious-preconscious-subliminal processing hierarchy. Uses nonlinear Schrödinger-type equations in imaginary time with non-Hermitian Hamiltonians to unify sensory encoding and conscious access.Votes: 0GitHub stars: 3
- Non Hermitian Gnw ConsciousnessNon-Hermitian potential well formalism for the subliminal-preconscious-conscious processing hierarchy in the Global Neuronal Workspace. Uses nonlinear Schrödinger-type equation in imaginary time with non-Hermitian, non-normal Hamiltonian to model conscious access as bound state emergence. Activation: GNW, consciousness, non-Hermitian, neural field theory, bound states, sensory processing hierarchy, cloud functions, global neuronal workspace.Votes: 0GitHub stars: 3
- Non Normal Covariance Spectra RnnFree-probability approach to stationary covariance spectra of discrete-time non-normal random recurrent dynamics - derives closed functional equation for moment generating function of limiting stationary covariance spectrum, analyzes tail eigenvalue behavior in critical regime, and shows continuous-time analog leads to infinite Schwinger-Dyson hierarchy instead of closed scalar equationVotes: 0GitHub stars: 3
- Novel Deep Neural Network Classifier Characterization Metrics With Applications To Dataless Evaluation**arXiv ID:** 2407.13000 **Authors:** Nathaniel Dean, Dilip Sarkar **Published:** 2024-07-17T20:40:46Z **Abstract:** The mainstream AI community has seen a rise in large-scale open-source classifiers, often pre-trained on vast datasets and tested on standard benchmarks; however, users facing diverse needs and limited, expensive test data may be overwhelmed by available choices. Deep Neural Network (DNN) classifiers undergo training, validation, and testing phases using example dataset, with t...Votes: 0GitHub stars: 3