A new recurrent neural network based on B-splinefunctionapproximation is presented. The network can be easily trained and its training converges more quickly.
提出一种新的基于基本样条逼近的循环神经网络，该网络易于训练且收敛速度快。
2
The meshing stiffness is calculated by employing 3-dimensional FEM and its function is formed by cubic spline interpolation and approximation of the discrete mesh points in a mesh period.