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。
A new recurrent neural network based on B-spline function approximation is presented. The network can be easily trained and its training converges more quickly.
该策略是建立在用基本样条函数实现BLDCM模糊神经网络速度控制器新方法基础之上。
This strategy absorbs a basic sample function to implement the fuzzy neural network speed controller.
对经过预处理的测试数据进行三次样条插值,得到基本时间序列。
First, the testing data must be interpolated and the basic time series must be built.
应用推荐