We solve the inverse problem using the conjugate gradient (CG) method, using Akaike's InformationCriterion (AIC) aic to truncate the CG expansion.
通过应用共轭梯度法来解决反演问题,应用 赤池弘次的AIC信息准则来 截短 共轭梯度扩大。
2
Subspace informationcriterion is a new criterion for model selection, it gives an unbiased estimate for the generalization error under some assumptions.
指出子空间信息准则是模型选择的一种新准则,它在一些假设条件下,给出推广误差的一种无偏估计。
3
Results We demonstrate that the Bayesian informationcriterion and decision theory are the most appropriate model-selection criteria because of their high accuracy and precision.