本文共 2183 字，大约阅读时间需要 7 分钟。

本章讲解了单层神经网络的学习规则。

This chapter explains the learning rulesfor a single-layer neural network.

第3章讨论了多层神经网络的学习规则。

The learning rules for a multi-layer neuralnetwork are addressed in Chapter 3.

神经网络的节点（Nodes of a Neural Network）

每当我们学到东西时，大脑就储存知识。

Whenever we learn something, our brainstores the knowledge.

计算机使用存储器来存储信息。

The computer uses memory to storeinformation.

虽然大脑和存储器都存储信息，但是二者的机制是非常不同的。

Although they both store information, theirmechanisms are very different.

计算机在指定位置存储信息，而大脑则是改变神经元之间的联系。

The computer stores information atspecified locations of the memory, while the brain alters the association ofneurons.

神经元本身没有存储能力，它只是将信号从一个神经元传递到另一个神经元。

The neuron itself has no storagecapability; it just transmits signals from one neurons to the other.

大脑是由这些神经元组成的巨大网络，神经元之间的联系形成了特定的信息。

The brain is a gigantic network of theseneurons, and the association of the neurons forms specific information.

神经网络模仿大脑的工作机制。

The neural network imitates the mechanismof the brain.

由于大脑是由众多神经元的连接构成的，神经网络是由众多节点的连接构成的，这些节点对应于大脑神经元。

As the brain is composed of connections ofnumerous neurons, the neural network is constructed with connections of nodes,which are elements that correspond to the neurons of the brain.

神经网络模仿神经元之间的联系使用权值，这是大脑最重要的工作机制。

The neural network mimics the neurons’association, which is the most important mechanism of the brain, using theweight value.

下表总结了大脑和神经网络之间的类比关系。

The following table summarizes the analogybetween the brain and neural network.

使用语言进一步解释这一点可能会导致更多的混淆。

Explaining this any further using text maycause more confusion.

通过一个简单的例子来更好地理解神经网络的机制。

Look at a simple example for a betterunderstanding of the neural network’s mechanism.

考虑一个三输入的神经网络节点，如图2-2所示。

Consider a node that receives three inputs,as shown in Figure 2-2.

图2-2 三输入的神经网络节点A node that receives threeinputs

图中的圆圈和箭头分别表示节点和信号流。

The circle and arrow of the figure denotethe node and signal flow, respectively.

也就是说，神经网络的信息以权值和偏置的形式存储。

In other words, the information of theneural net is stored in the form of weights and bias.

来自外部的输入信号在到达节点之前乘以权重。

The input signal from the outside ismultiplied by the weight before it reaches the node.

——本文译自Phil Kim所著的《Matlab Deep Learning》

更多精彩文章请关注微信号：