证明了一个分类网络的测试集正确率是该网络推广能力的极大似然估计；

And the accuracy rate of a classification network is explained as the maximum likelihood estimation of the generalization ability.

youdao

与极限平衡法和极大似然法的估计结果进行了比较，可以看出，神经网络方法具有推广预测精度高、自学习功能强、考虑不确定性能力强等特点。

The learned knowledge is then used for extrapolating prediction of the safety factor of new slope, Compared with the safety factors predicted by the limit equilibrium and m…

youdao

与极限平衡法和极大似然法的估计结果进行了比较，可以看出，神经网络方法具有推广预测精度高、自学习功能强、考虑不确定性能力强等特点。

The learned knowledge is then used for extrapolating prediction of the safety factor of new slope, Compared with the safety factors predicted by the limit equilibrium and maximum likelihood …

youdao