正文翻譯

I will quickly explain what the huge deep learning rage is all about.

我將快速解釋“深度學(xué)習狂潮”到底是怎么回事

This graph depicts a neural network that we build and simulate on a computer.

這張示意圖傳達了我們?nèi)祟愒谟嬎銠C上構(gòu)建和模擬的神經(jīng)網(wǎng)絡(luò)。

It is a very crude approximation of the human brain.

神經(jīng)網(wǎng)絡(luò)和人腦有著一種非常粗糙的近似

The leftmost layer denotes inputs, which can be, for instance, the pixels of an input image.

最左邊的層是輸入層，例如可以輸入圖像的像素

The rightmost layer is the output, which can be, for instance, a decision,whether the image depicts a horse or not.

最右邊的層是輸出層，它可以輸出一個判決，無論圖像是否描繪了一匹馬。

After we have given many inputs to the neural network,in its hidden layers, it will learn to figure out a way to recognize different classes of inputs, such as horses, people or school buses.

在我們?yōu)樯窠?jīng)網(wǎng)絡(luò)輸入了很多數(shù)據(jù)之后，它的隱藏層中將學(xué)習出一種方法，識別不同類別的輸出，例如馬，人或校車。

What is really surprising is that it's quite faithful to the way the brain does represent obxts on a lower level.

真正令人感覺神奇的是，這與大腦皮層在較淺層次表述物體的方式上相當吻合。

It has a very similar edge detector.

都有著非常類似的邊緣檢測器

And, it also works for audio:Here you can find the difference between the neurons in the hearing system of a cat,versus a simulated neural network on the same audio signals.

另外，神經(jīng)網(wǎng)絡(luò)的輸入輸出層還適用于音頻：從這張圖你可以找出貓咪的聽覺系統(tǒng)中神經(jīng)元與模擬神經(jīng)網(wǎng)絡(luò)在相同音頻信號處理上的差異

I mean, come on, this is amazing!

我是說，神經(jīng)網(wǎng)絡(luò)的運轉(zhuǎn)，這也太神奇了吧！

What is the deep learning part of it all?

那到底什么是深度學(xué)習呢？

Well it means that our neural network has multiple hidden layers on top of each other.

很好理解，就是我們的神經(jīng)網(wǎng)絡(luò)彼此之間有多個隱藏層

A combination of obxt parts yield obxts models, and so on.

再由對象物體的局部組合成對象模型，依此類推等等

This kind of hierarchy provides us very powerful capabilities.

神經(jīng)網(wǎng)絡(luò)這種層次結(jié)構(gòu)為我們提供了非常強大的能力

For instance, in this traffic sign recognition contest,the second place was taken by humans,but what's more interesting, is that the first place was not taken by humans,
it was taken a by a neural network algorithm.

例如，在這個交通標志識別競賽中，拿第二名的是人類，便更好玩的是，拿第一名不是人類，是神經(jīng)網(wǎng)絡(luò)算法。

評論翻譯