The algorithm uses the hinging hyperplanes model that uses hinging hyperplanes as basis functions in expansion.
该算法使用的“链接超平面”模型，也就是以“链接超平面”作为基函数。
In particular, when regression functions are linear, these sets become hyperplanes in explanatory variables Spaces.
特别地，当回归函数线性时，这类集合就是解释变量空间中的超平面。
The hinging hyperplanes model is improved and an indirect smooth approximation algorithm based on hinge-finding algorithm is proposed.
改进了链接超平面模型，并在找链接算法的基础上给出了一个处处光滑的间接光滑逼近算法。
The method is based on analytical results characterizing the solutions to a class of optimization problems that determine support hyperplanes of the response set.
在此基础上，利用凸集的性质提出了一种求解响应集的支撑超平面法，它是利用响应集的支撑超平面将问题转化为求解一类优化问题的解。
Distributions of the first hitting place and first hitting time for a conditioned Brownian motion to a hyperplane as well as its maximum excursions before hitting the hyperplanes are given.
给出了一类条件布朗运动关于超平面的首中位置与首中时间的分布，也给出了在首中超平面之前条件布朗运动的极大游程的分布。
Distributions of the first hitting place and first hitting time for a conditioned Brownian motion to a hyperplane as well as its maximum excursions before hitting the hyperplanes are given.
给出了一类条件布朗运动关于超平面的首中位置与首中时间的分布，也给出了在首中超平面之前条件布朗运动的极大游程的分布。
应用推荐