delta规则就是依据这个误差的定义来定义的。
The delta rule is defined in terms of this definition of error.
结果表明:用L -M规则进行神经网络学习训练可使网络收敛快,误差小。
The network lessens quicker and the error less trained with the L-M rule .
由确定性退火技术构造学习规则用于优化分类器参数,目的是减少分类误差以及待识别空间的系统熵。
Learning rules are constructed according to deterministic annealing to optimize classifier parameters, on purpose to reduce classification error and system entropy of the space to be identified.
应用推荐