圖2-3 節點分層結構示意圖A layered structure ofnodes

圖2-3中的方形節點組稱為輸入層。

The group of square nodes in Figure 2-3 iscalled the input layer.

輸入層的節點僅僅充當將輸入訊號傳送到下一節點的通道。

The nodes of the input layer merely act asthe passage that transmits the input signals to the next nodes.

因此，它們不計算加權和與啟用函式。

Therefore, they do not calculate theweighted sum and activation function.

這是它們由正方形表示，並區別於其它圓形節點的原因。

This is the reason that they are indicatedby squares and distinguished from the other circular nodes.

相反，最右邊的節點組被稱為輸出層。

In contrast, the group of the rightmostnodes is called the output layer.

從這些節點輸出神經網路的最終結果。

The output from these nodes becomes thefinal result of the neural network.

輸入層和輸出層之間的分層稱為隱藏層。

The layers in between the input and outputlayers are called hidden layers.

它們之所以被如此命名，是因為它們不能從神經網路外部訪問。

They are given this name because they arenot accessible from the outside of the neural network.

神經網路已經從一個簡單的體系結構發展到一個越來越複雜的結構。

The neural network has been developed froma simple architecture to a more and more complex structure.

最初，神經網路的先驅只有一個非常簡單的結構，只有輸入和輸出層，稱為單層神經網路。

Initially, neural network pioneers had avery simple architecture with only input and output layers, which are calledsinglelayer neural networks.

當隱藏層被新增到單層神經網路時，從而產生了多層神經網路。

When hidden layers are added to asingle-layer neural network, this produces a multi-layer neural network.

因此，多層神經網路由輸入層、隱藏層和輸出層組成。

Therefore, the multi-layer neural networkconsists of an input layer, hidden layer(s), and output layer.

具有單個隱藏層的神經網路被稱為淺層神經網路或沒有新意的神經網路。

The neural network that has a single hiddenlayer is called a shallow neural network or a vanilla neural network.

包含兩個或多個隱藏層的多層神經網路被稱為深度神經網路。

A multi-layer neural network that containstwo or more hidden layers is called a deep neural network.

在實際應用中使用的大多數神經網路都是深度神經網路。

Most of the contemporary neural networksused in practical applications are deep neural networks.

下表總結了依賴於分層結構的神經網路分支。

The following table summarizes the branchesof the neural network depending on the layer architecture.

將多層神經網路按以上兩種型別進行分類的原因與其發展的歷史背景有關。

The reason that we classify the multi-layerneural network by these two types has to do with its historical background ofdevelopment.

神經網路從單層神經網路發展到淺層神經網路，再到深層神經網路。

The neural network started as thesingle-layer neural network and evolved to the shallow neural network, followedby the deep neural network.

自從淺層神經網路出現二十年後，直到二十世紀中葉深層神經網路才受到重視。

The deep neural network has not beenseriously highlighted until the mid-2000s, after two decades had passed sincethe development of the shallow neural network.

因此，長期以來，多層神經網路僅僅意味著單隱層神經網路。

Therefore, for a long time, the multi-layerneural network meant just the single hidden-layer neural network.

——本文譯自Phil Kim所著的《Matlab Deep Learning》

更多精彩文章請關注微訊號：