A LoRA-Based Approach to Fine-Tuning LLMs for Educational Guidance in Resource-Constrained Settings

Συγγραφείς: Hosen, Md Millat

Θεματικοί όροι: Computer Science - Artificial Intelligence, 68T05 (Learning and adaptive systems), 68T07 (Artificial intelligence and education)

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2504.15610

Artificial to Spiking Neural Networks Conversion with Calibration in Scientific Machine Learning: Artificial to spiking neural networks conversion with calibration in scientific machine learning

Συγγραφείς: Qian Zhang, Chenxi Wu, Adar Kahana, George Em Karniadakis, Youngeun Kim, Yuhang Li, Priyadarshini Panda

Πηγή: SIAM Journal on Scientific Computing. 47:C559-C577

Θεματικοί όροι: scientific machine learning, PINN, Learning and adaptive systems in artificial intelligence, Artificial neural networks and deep learning, spiking neural network

Περιγραφή αρχείου: application/xml

Σύνδεσμος πρόσβασης: https://zbmath.org/8037156
https://doi.org/10.1137/24m1643232

CoCoGen: Physically Consistent and Conditioned Score-Based Generative Models for Forward and Inverse Problems: CoCoGen: physically consistent and conditioned score-based generative models for forward and inverse problems

Συγγραφείς: Christian Jacobsen, Yilin Zhuang, Karthik Duraisamy

Πηγή: SIAM Journal on Scientific Computing. 47:C399-C425

Θεματικοί όροι: diffusion models, FOS: Computer and information sciences, Inverse problems for PDEs, Computer Science - Machine Learning, Partial differential equations of mathematical physics and other areas of application, generative AI, physical consistency, Learning and adaptive systems in artificial intelligence, computational physics, score-based generative models, conditional generative modeling, Machine Learning (cs.LG)

Περιγραφή αρχείου: application/xml

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2312.10527

Uncertainty-Penalized Direct Preference Optimization

Συγγραφείς: Houliston, Sam, Pace, Alizée, Immer, Alexander, Rätsch, Gunnar

Θεματικοί όροι: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Statistics - Machine Learning, Learning and adaptive systems in artificial intelligence

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2410.20187

Research on signal recognition method of acoustic beacon for underwater acoustic active and passive positioning dynamics system based on machine learning

Συγγραφείς: Xu, Jinjin

Πηγή: Journal of Combinatorial Mathematics and Combinatorial Computing. 124:159-171

Θεματικοί όροι: Signal theory (characterization, reconstruction, filtering, etc.), machine learning, signal recognition, Learning and adaptive systems in artificial intelligence, underwater acoustic active and passive positioning system, acoustic beacon

Περιγραφή αρχείου: application/xml

DeepONet Based Preconditioning Strategies for Solving Parametric Linear Systems of Equations: DeepONet based preconditioning strategies for solving parametric linear systems of equations

Συγγραφείς: Alena Kopaničáková, George Em Karniadakis

Πηγή: SIAM Journal on Scientific Computing. 47:C151-C181

Θεματικοί όροι: Large-scale problems in mathematical programming, Iterative numerical methods for linear systems, operator learning, Multigrid methods, domain decomposition for initial value and initial-boundary value problems involving PDEs, preconditioning, Learning and adaptive systems in artificial intelligence, FOS: Mathematics, Krylov methods, Preconditioners for iterative methods, spectral bias, Mathematics - Numerical Analysis, Numerical Analysis (math.NA), hybridization

Περιγραφή αρχείου: application/xml

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2401.02016

Limits of Learning Dynamical Systems: Limits of learning dynamical systems

Συγγραφείς: Tyrus Berry, Suddhasattwa Das

Πηγή: SIAM Review. 67:107-137

Θεματικοί όροι: iterative forecast, Learning and adaptive systems in artificial intelligence, 37M99, 37N30, 37A20, 37D25, Dynamical Systems (math.DS), reservoir computing, direct forecast, Approximation methods and numerical treatment of dynamical systems, matrix cocycle, Dynamical systems in numerical analysis, delay coordinates, stochastic stability, FOS: Mathematics, mixing, Nonuniformly hyperbolic systems (Lyapunov exponents, Pesin theory, etc.), Mathematics - Dynamical Systems, Lyapunov exponent

Περιγραφή αρχείου: application/xml

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2409.13493

Reinforcement Learning‐Based Prescribed Performance Formation Control for USVs With Collision Avoidance and Preserved Connectivity: Reinforcement learning-based prescribed performance formation control for USVs with collision avoidance and preserved connectivity

Συγγραφείς: Gengqi Li, Wei Wang, Liang Cao

Πηγή: International Journal of Robust and Nonlinear Control. 35:2996-3012

Θεματικοί όροι: reinforcement learning, optimal formation control, unmanned surface vehicles (USVs), Learning and adaptive systems in artificial intelligence, preserved connectivity, Automated systems (robots, etc.) in control theory, collision avoidance, monotone tube boundary function

Περιγραφή αρχείου: application/xml

Prescribed‐Time Optimal Formation Synchronous Tracking Control of UAV‐Ugvs Based on Reinforcement Learning: Prescribed-time optimal formation synchronous tracking control of UAV-UGVs based on reinforcement learning

Συγγραφείς: Shi‐Xun Xiong, Guo‐Ping Jiang, Yun‐Xia Zhu, Xiao‐Ming He, Shu‐Han Chen

Πηγή: International Journal of Robust and Nonlinear Control. 35:2437-2450

Θεματικοί όροι: optimal control, reinforcement learning, Learning and adaptive systems in artificial intelligence, Automated systems (robots, etc.) in control theory, Existence theories for optimal control problems involving partial differential equations, UAV-UGV formation, prescribed-time

Περιγραφή αρχείου: application/xml

Σύνδεσμος πρόσβασης: https://zbmath.org/8034848
https://doi.org/10.1002/rnc.7808

Automobile Insurance Fraud Detection Based on PSO-XGBoost Model and Interpretable Machine Learning Method: Automobile insurance fraud detection based on PSO-XGBoost model and interpretable machine learning method

Συγγραφείς: Ding, Ning, Ruan, Xiao, Wang, Hao, Liu, Yuan

Πηγή: Insurance: Mathematics and Economics. 120:51-60

Θεματικοί όροι: fraud detection, automobile insurance, SHAP, Actuarial mathematics, Learning and adaptive systems in artificial intelligence, PSO-XGBoost

Περιγραφή αρχείου: application/xml

Σύνδεσμος πρόσβασης: https://zbmath.org/7984120
https://doi.org/10.1016/j.insmatheco.2024.11.006

Adaptive Interface-PINNs (AdaI-PINNs): An Efficient Physics-Informed Neural Networks Framework for Interface Problems: Adaptive interface-PINNs (AdaI-PINNs): an efficient physics-informed neural networks framework for interface problems

Συγγραφείς: Roy, Sumanta, Annavarapu, Chandrasekhar, Roy, Pratanu, Sarma, Antareep Kumar

Πηγή: Communications in Computational Physics. 37:603-622

Θεματικοί όροι: FOS: Computer and information sciences, I-PINNs, Computer Science - Machine Learning, physics-informed machine learning, Learning and adaptive systems in artificial intelligence, interface problems, AdaI-PINNs, Computational methods for problems pertaining to mechanics of particles and systems, Machine Learning (cs.LG), domain decomposition, machine learning, Structured surfaces and interfaces, coexistent phases, PINN, Interface problems, diffusion-limited aggregation arising in equilibrium statistical mechanics, Partial differential equations and systems of partial differential equations with constant coefficients

Περιγραφή αρχείου: application/xml

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2406.04626

Learning large-scale industrial physics simulations

Συγγραφείς: Casenave, Fabien

Πηγή: European Mathematical Society Magazine. :5-13

Θεματικοί όροι: Learning and adaptive systems in artificial intelligence, FOS: Mathematics, Mathematics - Numerical Analysis, Numerical Analysis (math.NA), General theory of mathematical modeling

Περιγραφή αρχείου: application/xml

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2502.08295

How Much Data Is Sufficient to Learn High-Performing Algorithms?: How much data is sufficient to learn high-performing algorithms?

Συγγραφείς: Maria-Florina Balcan, Dan Deblasio, Travis Dick, Carl Kingsford, Tuomas Sandholm, Ellen Vitercik

Πηγή: Journal of the ACM. 71:1-58

Θεματικοί όροι: 0301 basic medicine, data-driven algorithm design, 0303 health sciences, 03 medical and health sciences, machine learning, computational biology, General topics in the theory of algorithms, Learning and adaptive systems in artificial intelligence, automated algorithm design, automated algorithm configuration

Περιγραφή αρχείου: application/xml

A Bayesian Approach for Learning Bayesian Network Structures: A Bayesian approach for learning Bayesian network structures

Συγγραφείς: Zareifard, Hamid, Tabar, Vahid Rezaei, Javidian, Mohammad Ali, Yozgatlıgil, Ceylan

Συνεισφορές: OpenMETU

Πηγή: Lobachevskii Journal of Mathematics. 45:4434-4447

Θεματικοί όροι: Bayesian network, directed acyclic graphs, structure learning, Estimation in multivariate analysis, Bayesian inference, Gibbs sampler, Learning and adaptive systems in artificial intelligence, Bayesian estimation, Monte Carlo, Probabilistic graphical models

Περιγραφή αρχείου: application/xml

Auto-weighted Bayesian Physics-Informed Neural Networks and robust estimations for multitask inverse problems in pore-scale imaging of dissolution: Auto-weighted Bayesian physics-informed neural networks and robust estimations for multitask inverse problems in pore-scale imaging of dissolution

Συγγραφείς: Sarah Perez, Philippe Poncet

Πηγή: Computational Geosciences. 28:1175-1215

Θεματικοί όροι: FOS: Computer and information sciences, Computer Science - Machine Learning, Bayesian physics-informed neural networks, uncertainty quantification, Learning and adaptive systems in artificial intelligence, Computer Science - Neural and Evolutionary Computing, Numerical Analysis (math.NA), Inverse problems in geophysics, artificial intelligence, imaging inverse problem, 01 natural sciences, Machine Learning (cs.LG), pore-scale porous media, multi-objective training, 0103 physical sciences, FOS: Mathematics, Geostatistics, Hamiltonian Monte Carlo, Mathematics - Numerical Analysis, Neural and Evolutionary Computing (cs.NE), 0105 earth and related environmental sciences

Περιγραφή αρχείου: application/xml

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2308.12864

New Douglas-Rashford Splitting Algorithms for Generalized DC Programming with Applications in Machine Learning: New Douglas-Rashford splitting algorithms for generalized DC programming with applications in machine learning

Συγγραφείς: Yonghong Yao, Lateef O. Jolaoso, Yekini Shehu, Jen-Chih Yao

Πηγή: Journal of Scientific Computing. 103

Θεματικοί όροι: machine learning, Numerical mathematical programming methods, DC programming, Nonlinear programming, Optimization and Control (math.OC), nonconvex optimization, Learning and adaptive systems in artificial intelligence, FOS: Mathematics, Nonconvex programming, global optimization, Douglas-Rachford splitting algorithm, Mathematics - Optimization and Control

Περιγραφή αρχείου: application/xml

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2404.14800

Self‐triggered control for linear systems based on hierarchical reinforcement learning: Self-triggered control for linear systems based on hierarchical reinforcement learning

Συγγραφείς: Wei Chen, Haiying Wan, Xiaoli Luan, Fei Liu

Πηγή: International Journal of Robust and Nonlinear Control. 34:9112-9129

Θεματικοί όροι: Hierarchical systems, 0209 industrial biotechnology, self-triggered control, Linear systems in control theory, model-free, Learning and adaptive systems in artificial intelligence, 0202 electrical engineering, electronic engineering, information engineering, 02 engineering and technology, hierarchical reinforcement learning

Περιγραφή αρχείου: application/xml

A multi-aggregator graph neural network for backbone exaction of fracture networks

Συγγραφείς: Zheng, Tianji, Sun, Chengcheng, Zhang, Jian, Ye, Jiawei, Rui, Xiaobin, Wang, Zhixiao

Πηγή: Computational Geosciences. 28:537-549

Θεματικοί όροι: inductive learning, Computational methods for problems pertaining to geophysics, backbone extraction, Learning and adaptive systems in artificial intelligence, graph neural network, discrete fracture networks

Περιγραφή αρχείου: application/xml

Impact of thermal radiations and viscous dissipation during the boundary layer non‐Newtonian fluid flow past a slender needle: Probed by machine learning: Impact of thermal radiations and viscous dissipation during the boundary layer non-Newtonian fluid flow past a slender needle: probed by machine learning

Συγγραφείς: Hongxing Yao, Asad Ullah, null Ikramullah, Adel M. Widyan, Ali Althobaiti, Hamiden Abd El‐Wahed Khalifa

Πηγή: ZAMM - Journal of Applied Mathematics and Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik. 105

Θεματικοί όροι: similarity transform, Non-Newtonian fluids, Learning and adaptive systems in artificial intelligence, Levenberg-Marquardt algorithm: parametric study, Joule heating, Magnetohydrodynamics and electrohydrodynamics, Basic methods in fluid mechanics, Diffusive and convective heat and mass transfer, heat flow, magnetic field, artificial neural network, Artificial neural networks and deep learning, Casson fluid

Περιγραφή αρχείου: application/xml

Random features and polynomial rules

Συγγραφείς: Fabian Aguirre-Lopez, Silvio Franz, Mauro Pastore

Πηγή: SciPost Physics, Vol 18, Iss 1, p 039 (2025)

Θεματικοί όροι: FOS: Computer and information sciences, Computer Science - Machine Learning, Physics, QC1-999, Learning and adaptive systems in artificial intelligence, FOS: Physical sciences, Disordered Systems and Neural Networks (cond-mat.dis-nn), Condensed Matter - Disordered Systems and Neural Networks, Disordered systems (random Ising models, random Schrödinger operators, etc.) in equilibrium statistical mechanics, Artificial neural networks and deep learning, Machine Learning (cs.LG)

Περιγραφή αρχείου: application/xml; application/pdf

Σύνδεσμος πρόσβασης: http://arxiv.org/abs/2402.10164
https://zbmath.org/7982799
https://doi.org/10.21468/scipostphys.18.1.039
https://doaj.org/article/04cae1a59a9b49168a087650d8e904b0
https://scipost.org/10.21468/SciPostPhys.18.1.039
https://doi.org/10.21468/SciPostPhys.18.1.039
https://hdl.handle.net/11587/552001