In the process of application of Improved BP algorithm in PNN, the input functions and the network weight functions are represented as expansion of a same orthogonal function basis.
在改进BP算法与网络训练的结合过程中，权函数及输入函数皆被用同一正交基函数展开。
In consideration of the complexity of the aggregation operation of time in process neural networks, a new learning algorithm based on function orthogonal basis expansion is proposed.
该文在考虑过程神经网络对时间聚合运算的复杂性的基础上，提出了一种基于函数正交基展开的学习算法。
By introducing a group of function orthogonal basis into the input space, the input functions and the network weight functions are expressed in the expansion form.
在输入空间中引入一组函数正交基，将输入函数和网络权函数表示为该组正交基的展开形式，利用基函数的正交性简化过程神经元聚合运算。
By introducing a group of function orthogonal basis into the input space, the input functions and the network weight functions are expressed in the expansion form.
在输入空间中引入一组函数正交基，将输入函数和网络权函数表示为该组正交基的展开形式，利用基函数的正交性简化过程神经元聚合运算。
应用推荐