Results 241 to 250 of about 2,360,976 (284)
Some of the next articles are maybe not open access.
Error estimation and error bounds for neural networks
Proceedings 1995 Second New Zealand International Two-Stream Conference on Artificial Neural Networks and Expert Systems, 2002A method is proposed to estimate the standard error of predicted values in multilayer perceptron (MLP). It is based on likelihood theory. It holds for all feedforward networks, irrespective of the topology or the specific task at hand. In addition, the bounds on a neural network with perturbed weights and inputs is analytically derived.
Hualou Liang, Guiliang Dai
openaire +1 more source
Estimation of the GSSM calibration error
Applied Optics, 2016The calibration of the tertiary mirror of the Thirty Meter Telescope, also known as the giant science steering mirror (GSSM), is a step of great significance during its testing process. Systematic, drift, and random errors constitute the major limitations to the accuracy of the calibration measurements.
Linchu, Han +3 more
openaire +2 more sources
Generalization error of ensemble estimators
Proceedings of International Conference on Neural Networks (ICNN'96), 2002It has been empirically shown that a better estimate with less generalization error can be obtained by averaging outputs of multiple estimators. This paper presents an analytical result for the generalization error of ensemble estimators. First, we derive a general expression of the ensemble generalization error by using factors of interest (bias ...
Naonori Ueda, Ryohei Nakano
openaire +1 more source
2003
In this chapter we assume the spacetime K is foliated by a double null canonical foliation that satisfies the assumptions $$O \leqslant \epsilon_0 ,\,D \leqslant \epsilon_0 ,$$ (6.0.1) and we make use of the inequality proved in Theorem M7 $$R \leqslant cQ_K^{\frac{1} {2}} .$$ (6.0.2)
Sergiu Klainerman, Francesco Nicolò
openaire +1 more source
In this chapter we assume the spacetime K is foliated by a double null canonical foliation that satisfies the assumptions $$O \leqslant \epsilon_0 ,\,D \leqslant \epsilon_0 ,$$ (6.0.1) and we make use of the inequality proved in Theorem M7 $$R \leqslant cQ_K^{\frac{1} {2}} .$$ (6.0.2)
Sergiu Klainerman, Francesco Nicolò
openaire +1 more source
Bounds and error estimates for radiosity
Proceedings of the 21st annual conference on Computer graphics and interactive techniques - SIGGRAPH '94, 1994We present a method for determining a posteriori bounds and estimates for local and total errors in radiosity solutions. The ability to obtain bounds and estimates for the total error is crucial fro reliably judging the acceptability of a solution. Realistic estimates of the local error improve the efficiency of adaptive radiosity algorithms, such as ...
Dani Lischinski +2 more
openaire +1 more source
1998
In the conceptual idea described in Chapter 6.1, it was assumed that the mean of the sample would deviate from that of the population from which it was collected. This therefore raises the question of how “precisely” does the mean value of the sample reflect that of the population. In other words, how large is the uncertainty of the mean value, or what
openaire +1 more source
In the conceptual idea described in Chapter 6.1, it was assumed that the mean of the sample would deviate from that of the population from which it was collected. This therefore raises the question of how “precisely” does the mean value of the sample reflect that of the population. In other words, how large is the uncertainty of the mean value, or what
openaire +1 more source
On Weak Residual Error Estimation
SIAM Journal on Scientific Computing, 1996The author develops a general framework for weak residual error estimators applied to various types of boundary value problems in connection with finite element and finite volume approximations. The paper illustrates basic ideas commonly shared by various applications in error estimation and adaptive computation. Some numerical results are given.
openaire +1 more source
Local error estimates in quadrature
BIT, 1991zbMATH Open Web Interface contents unavailable due to conflicting licenses.
ROMANI, FRANCESCO, Favati P, Lotti G.
openaire +5 more sources
Error estimation and control for ODEs
Journal of Scientific Computing, 2005zbMATH Open Web Interface contents unavailable due to conflicting licenses.
openaire +2 more sources
Microstructural Decomposition Error Estimates
ZAMM - Journal of Applied Mathematics and Mechanics / Zeitschrift für Angewandte Mathematik und Mechanik, 1999AbstractComputational simulations of interacting microstructure in solid structures, with methods such as the finite element method, require solutions to numerically enormous boundary value problems. The primary objective of this work is to introduce a‐posteriori error bounds for a domain decomposition which can be used to reduce the computational ...
Zohdi, T., Wriggers, P.
openaire +1 more source