深度學習基礎（二）—— 從多層感知機（MLP）到卷積神經網路（CNN）
經典的多層感知機（Multi-Layer Perceptron）形式上是全連線（fully-connected）的鄰接網路（adjacent network）。
That is, every neuron in the network is connected to every neuron in adjacent layers.
Local receptive fields
全連線的多層感知機中，輸入視為（或者需轉化為）一個列向量。而在卷積神經網路中，以手寫字元識別為例，輸入不再 reshape 為 (28*28, 1) 的列向量，而是作為
That region in the input image is called the local receptive field for the hidden neuron. It’s a little window on the input pixels. Each connection learns a weight（one single weight，也即整個
Shared weights and biases
注意對應關係，是左上角對應左上角，後四列是利用不到的？
第
該隱層神經元的輸出為：
The network structure I’ve described so far can detect just a single kind of localized feature. To do image recognition we’ll need more than one feature map（特徵對映）. And so a complete convolutional layer consists of several different feature maps:
feature map：filter，kernel
In the example shown, there are 3 feature maps. Each feature map is defined by a set of 5×5 shared weights, and a single shared bias. The result is that the network can detect 3 different kinds of features（特徵檢測）, with each feature being detectable across the entire image.
I’ve shown just 3 feature maps, to keep the diagram above simple. However, in practice convolutional networks may use more (and perhaps many more) feature maps. One of the early convolutional networks, LeNet-5, used 6 feature maps, each associated to a 5×5 local receptive field, to recognize MNIST digits. So the example illustrated above is actually pretty close to LeNet-5. In the examples we develop later in the chapter we’ll use convolutional layers with 20 and 40 feature maps. Let’s take a quick peek at some of the features which are learned*