n bit output 位输出
On the one hand, the more n influences an output node, the more n affects the net's overall error.
一方面，n 影响一个输出节点越多，n 造成网络整体的误差也越多。
where j varies over all the output nodes that receive input from n. Moreover, the basic outline of a back-propagation algorithm runs like this.
这里每个从 n 接收输入的输出节点 j 都不同。 关于反向传播算法的基本情况大致如此。
where d(n) for a hidden node n, turns on (1) how much n influences any given output node; and (2) how much that output node itself influences the overall error of the net.
其中 d(n) 是隐藏节点 n 的函数，让我们来看（1）n 对任何给出的输出节点有多大影响；（2）输出节点本身对网络整体的误差有多少影响。
应用推荐