聚类的准则函数 误差平方和准则（sum-of-squared-error criterion）： k Je X mi 2 i 1 X Ci 其中X∈Ci，mi是Ci的质心 Je即所有样本的平方误差和。
基于16个网页-相关网页
结果表明，与传统的基于误差平方和准则的学习算法相比，采用模糊学习算法可以大大简化网络结构，有效提高模拟精度和效率。
The modeling results showed that the introduction of fuzzy learning method can not only simplify the structure of neural network, but also effectively improve the modeling accuracy and efficiency.
基于模糊熵准则和误差平方和准则建立了模糊学习算法，基于该模糊学习算法，应用BP神经网络对柜式空调机组的性能进行了模拟。
Based on fuzzy entropy rule and sum-squared error rule, a fuzzy learning method was presented. According to this method, BP neural network was used to model the performance of air-conditioning units.
利用BIC准则及残差平方和最小原则得到振梁加速度计的最佳误差模型。
The rules of BIC and minimum residual sum of squares are used to gain the optimum error model.
应用推荐