Showing 1 - 10 of 12
Persistent link: https://www.econbiz.de/10011285515
This article uses a sequentialized experimental design to select simulation input combinations for global optimization … “efficient global optimization” (EGO) through the introduction of an improved estimator of the Kriging predictor variance; this …
Persistent link: https://www.econbiz.de/10010994014
A Manhattan search algorithm to minimize artificial neural network error function is outlined in this paper. From an existing position in Cartesian coordinate, a search vector moves in orthogonal directions to locate minimum function value. The search algorithm computes optimized step length for...
Persistent link: https://www.econbiz.de/10010998486
yet simulated. These predictions and their variances are used by efficient global optimization"(EGO), to balance local and …
Persistent link: https://www.econbiz.de/10011144439
optimization, based on Kriging (also called Gaussian process or spatial correlation modeling); this Kriging is used to analyze the … improvement" (EI) in "efficient global optimization" (EGO) through the introduction of an unbiased estimator of the Kriging …
Persistent link: https://www.econbiz.de/10011092889
Abstract: This paper investigates two related questions: (1) How to derive a confidence interval for the output of a combination of simulation inputs not yet simulated? (2) How to select the next combination to be simulated when searching for the optimal combination? To answer these questions,...
Persistent link: https://www.econbiz.de/10011091634
Persistent link: https://www.econbiz.de/10010196962
Persistent link: https://www.econbiz.de/10011487609
Persistent link: https://www.econbiz.de/10013258989
This paper is aimed at presenting application of bootstrap interval estimation methods to the assessment of financial investment’s effectiveness and risk. At first, we give an overview of various methods of bootstrap confidence interval estimation, i.e. bootstrap-t interval, percentile...
Persistent link: https://www.econbiz.de/10012887711