感知器培训规则是基于这样一种思路—权系数的调整是由目标和输出的差分方程表达式决定。
The perceptron training rule is based on the idea that weight modification is best determined by some fraction of the difference between target and output.
通过对相应的多因子变量灰微分方程进行参数辨识,求得各影响因素的权系数。
Competence coefficients of each influential factor are solved through parameters identification of related multi-factor variable grey differential equation.
其中在多重模糊推理神经网络中,通过求解模糊关系方程的方法来确定网络的权值。
In the neural network corresponding to multidimensional fuzzy inference, the weights are adjusted by means of solution to fuzzy relation equation.
应用推荐