本文简要地介绍与分析了变位系数的一般选取方法即试算法与微分逼近法。
This paper gives a brief description and analysis of two general methods of selectingcorrection factors, those are, by cut and trial and by differential approximation.
分析了光流计算中产生时域微分估计误差的各种因素，提出了光流的逐次逼近计算模型。
The factors, which introduce the error of temporal differential estimation are, analyzed. The successive approximation calculation model for the optical flow estimation is put forward.
本文用多层前向神经网络求解该非线性偏微分方程，从而逼近非线性系统的中心流形。
In this paper, multi-layer feedforward neural networks are used to solve the nonlinear partial differential equation, and approach the centre manifold of the nonlinear system.
应用推荐