Hierarchical mixtures of experts and the EM algorithm
Neural Computation
The approximation power of moving least-squares
Mathematics of Computation
An introduction to boosting and leveraging
Advanced lectures on machine learning
A tutorial on support vector regression
Statistics and Computing
Kriging interpolation in simulation: a survey
WSC '04 Proceedings of the 36th conference on Winter simulation
Neural Networks
Neural Networks: A Comprehensive Foundation (3rd Edition)
Neural Networks: A Comprehensive Foundation (3rd Edition)
State-of-the-Art Review: A User's Guide to the Brave New World of Designing Simulation Experiments
INFORMS Journal on Computing
A study of cross-validation and bootstrap for accuracy estimation and model selection
IJCAI'95 Proceedings of the 14th international joint conference on Artificial intelligence - Volume 2
Approximation of the critical buckling factor for composite panels
Structural and Multidisciplinary Optimization
Performance of an ensemble of ordinary, universal, non-stationary and limit Kriging predictors
Structural and Multidisciplinary Optimization
Bi-objective optimization of pylon-engine-nacelle assembly: weight vs. tip clearance criterion
Structural and Multidisciplinary Optimization
| Hi-index | 0.00 |
An automatic method to combine several local surrogate models is presented. This method is intended to build accurate and smooth approximation of discontinuous functions that are to be used in structural optimization problems. It strongly relies on the Expectation驴Maximization (EM) algorithm for Gaussian mixture models (GMM). To the end of regression, the inputs are clustered together with their output values by means of parameter estimation of the joint distribution. A local expert is then built (linear, quadratic, artificial neural network, moving least squares) on each cluster. Lastly, the local experts are combined using the Gaussian mixture model parameters found by the EM algorithm to obtain a global model. This method is tested over both mathematical test cases and an engineering optimization problem from aeronautics and is found to improve the accuracy of the approximation.