Results 111 to 120 of about 306,033 (284)

A Physics Constrained Machine Learning Pipeline for Young's Modulus Prediction in Multimaterial Hyperelastic Cylinders Guided by Contact Mechanics

Advanced Intelligent Discovery, EarlyView.
A physics‐guided machine learning framework estimates Young's modulus in multilayered multimaterial hyperelastic cylinders using contact mechanics. A semiempirical stiffness law is embedded into a custom neural network, ensuring physically consistent predictions. Validation against experimental and numerical data on C.
Christoforos Rekatsinas, Panagiotis Krokidas, Vasileios Vavourakis, Clara Essmann, George Giannakopoulos   +4 more
wiley   +1 more source

Factorization Machine‐Based Active Learning for Functional Materials Design with Optimal Initial Data

Advanced Intelligent Discovery, EarlyView.
This work investigates the optimal initial data size for surrogate‐based active learning in functional material optimization. Using factorization machine (FM)‐based quadratic unconstrained binary optimization (QUBO) surrogates and averaged piecewise linear regression, we show that adequate initial data accelerates convergence, enhances efficiency, and ...
Seongmin Kim, In‐Saeng Suh
wiley   +1 more source

AN ALGORITHM TO MINIMIZE SINGLE VARIABLE POLYNOMIAL, FUNCTIONS FROM ANY STARTING POINT WITH QUADRATIC CONVERGENCE

South African Journal of Industrial Engineering, 2012
Search methods often display non-convergence or excessive convergence time on certain classes of nonlinear functions arising in engineering design. The authors will define a new geometric -programming based search method for single variable polynomials ...
James Thorne, Doran Greening, Robert E.D. Woolsey   +2 more
doaj  

A quadratically converging algorithm of multidimensional scaling

Informatica, 1996
Summary: Multidimensional scaling (MDS) is a well-known technique for the analysis of multidimensional data. The most important part of the implementation of MDS is the minimization of the STRESS function. The convergence rate of known local minimization algorithms of the STRESS function is no better than superlinear.
openaire   +2 more sources

Robust Reinforcement Learning Control Framework for a Quadrotor Unmanned Aerial Vehicle Using Critic Neural Network

Advanced Intelligent Systems, Volume 7, Issue 3, March 2025.
Quadrotor unmanned aerial vehicle control is critical to maintain flight safety and efficiency, especially when facing external disturbances and model uncertainties. This article presents a robust reinforcement learning control scheme to deal with these challenges.
Yu Cai, Yefeng Yang, Tao Huang, Boyang Li   +3 more
wiley   +1 more source

Rates of convergence of quadratic rank statistics

Journal of Multivariate Analysis, 1977
AbstractThe rates of convergence of the distribution function of quadratic rank statistics to the X2-distribution under hypothesis and near alternatives are investigated. The considered quadratic rank statistics are used for testing the multivariate hypothesis of randomness. The method suggested by Jurečková [7] is applied.
openaire   +2 more sources

Real‐Time Sampling‐Based Model Predictive Control Based on Reverse Kullback–Leibler Divergence and Its Adaptive Acceleration

Advanced Intelligent Systems, EarlyView.
This study presents a new sampling‐based model predictive control minimizing reverse Kullback‐Leibler divergence to quickly find a local optimum. In addition, a modified Nesterov's acceleration method is introduced for faster convergence. The method is effective for real‐time simulations and real‐world operability improvement on a force‐driven mobile ...
Taisuke Kobayashi, Kota Fukumoto
wiley   +1 more source

Convergence of approximate solutions to nonlinear Caputo nabla fractional difference equations with boundary conditions

Electronic Journal of Differential Equations, 2020
This article studies a boundary value problem for a nonlinear Caputo nabla fractional difference equation. We obtain quadratic convergence results for this equation using the generalized quasi-linearization method.
Xiang Liu, Baoguo Jia, Scott Gensler, Lynn Erbe, Allan Peterson   +4 more
doaj  

A Novel Contact‐Implicit Trajectory Optimization Framework for Quadruped Locomotion without Fixed Contact Sequences

Advanced Intelligent Systems, EarlyView.
Legged robots have advanced in environmental interaction through contact, but most works rely on fixed contact sequences. This work presents a new method based on an indirect optimization method for legged robots to automatically generate contact sequences for complex movements.
Yaowei Chen, Jie Zhang, Ming Lyu
wiley   +1 more source

Bridging High‐Fidelity Simulations and Physics‐Based Learning using a Surrogate Model for Soft Robot Control

Advanced Intelligent Systems, EarlyView.
A surrogate‐model‐based framework is proposed for combining high‐fidelity finite element method and efficient physics simulations to enable fast, accurate soft robot simulation for reinforcement learning, validated through sim‐to‐real experiments. Soft robotics holds immense promise for applications requiring adaptability and compliant interactions ...
Taehwa Hong, Jungjae Lee, Byung‐Hyun Song, Yong‐Lae Park   +3 more
wiley   +1 more source