更改
跳到导航
跳到搜索
第80行：
第80行： − + 第90行：
第90行： − An ''input neuron'' has no predecessor but serves as input interface for the whole network. Similarly an ''output neuron'' has no successor and thus serves as output interface of the whole network.+
→神经元（Neurons）
====神经元（Neurons）====
====神经元（Neurons）====
A neuron with label <math>j</math> receiving an input <math>p_j(t)</math> from predecessor neurons consists of the following components:<ref name=Zell1994ch5.2 />
A neuron with label <math>i</math> receiving an input <math>p_j(t)</math> from predecessor neurons consists of the following components:
* an ''activation'' <math>a_j(t)</math>, depending on a discrete time parameter,
* an ''activation'' <math>a_j(t)</math>, depending on a discrete time parameter,
Often the output function is simply the [[Identity function]].
Often the output function is simply the [[Identity function]].
一个“输入神经元”没有前驱，但作为整个网络的输入接口。同样地，一个“输出神经元”没有后继而作为整个网络的输出接口。
====连接和权重（Connections and weights）====
====连接和权重（Connections and weights）====