| 释义 |
back·prop·a·ga·tion AHD[băkʹprŏp'ə-gāʹshən] D.J.[ˈbækˌprɒpəˈgeɪʃən]K.K.[ˈbækˌprɑpəˈgeʃən]n.（名词）- A common method of training a neural net in which the initial system output is compared to the desired output, and the system is adjusted until the difference between the two is minimized.反向传播，逆传送：训练神经系统网络的普遍方式，将初始系统输出同要求系统输出相比较，然后将系统调整到两输出间差距最小的状态
|