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 orthogonalfunction 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。
2
In consideration of the complexity of the aggregation operation of time in process neural networks, a new learning algorithm based on functionorthogonal 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。
3
By introducing a group of functionorthogonal basis into the input space, the input functions and the network weight functions are expressed in the expansion form.