为什么我们需要生成对抗网络：-(Why do we need Generative Adversarial Network: -)

If we show a lot and lots of pictures of a person and car to a neural network and tell the network which one is a car and which one is a person’s picture then eventually this network learns to differentiate between a person and a car. So, when you feed a new picture of a car or a person it will tell whether it’s a person or a car as shown in Figure 1.1. Basically, what this network does is that it constructs a structure that is meaningful if we look at it.

如果我们在神经网络中显示很多人和汽车的图片，并告诉网络哪一个是汽车，哪一个是一个人的图片，那么最终该网络将学会区分人和汽车。 因此，当您提供汽车或人的新照片时，它将告诉您是人还是汽车，如图1.1所示。 基本上，该网络所做的就是构造一个有意义的结构(如果我们看一下的话)。

But if you tell this network to generate a new unseen picture of a person or a car then it won’t be able to do that as shown in Figure 1.2.

但是，如果您告诉该网络生成一个新的看不见的人或汽车的图片，那么它将无法做到这一点，如图1.2所示。

Most often we need to generate new samples of the same Input distribution and for that, we need a generative model

通常，我们需要生成具有相同输入分布的新样本，为此，我们需要生成模型

生成网络：-(Generative Network: -)

If we feed these three types(Figure 2) of data to a Generative neural network then the network learned model will look like Figure 3. When we try to generate a sample form this trained generative neural network then it will generate Figure 4 since this is similar to the average of all three-input distribution. But by looking at it we say no this sample does not belong to any of the input data distribution. So, how to solve this problem. And the answer is randomness. So, the Generative models add randomness to generate indistinguishable results.

如果我们将这三种类型的数据(图2)输入到生成型神经网络，则网络学习模型将如图3所示。当我们尝试从经过训练的生成型神经网络生成样本时，它将生成图4，因为这是类似于所有三项输入分布的平均值。 但是通过查看它，我们可以说这个样本不属于任何输入数据分布。 那么，如何解决这个问题。 答案是随机性。 因此，生成模型会增加随机性以产生难以区分的结果。

对抗网络：-(Adversarial Network: -)

Suppose we want to train a network to correctly identify the digits from 0 to 9. We feed lots and lots of images of numbers 0,1, 2, and so on. While the training network gets rewarded for the right prediction and the wrong prediction network gives feedback and the network will adjust its weights accordingly and this process will get repeated over and over for all the images of all digits. But we as a human does not behave like this.

假设我们要训练一个网络以正确识别0到9之间的数字。我们输入大量的数字0、1、2等图像，依此类推。 当训练网络因正确的预测而获得奖励而错误的预测网络给出反馈时，网络将相应地调整其权重，并且该过程将针对所有数字的所有图像反复进行。 但是我们作为一个人并不像这样。

For example — Suppose as a teacher and you are teaching a child how to recognize 0–9 digits. For numbers 0, 2, 3, 4, 5, 6, 8, 9 he can get the right answer 70% time. But when he gets 1 and 7 digits, he will be like 50–50(he won’t be able to tell). Because digits 1 and 7 looks similar to him. So, when you notice this then you start focusing on 1 and 7 where he faces most of the problem. And this kind of balance possible in humans because if you keep asking the same thing where he is failing then eventually, he will get demotivated and will give up, but that’s not the case with neural networks because NN doesn’t have feelings. We can train the network for these errors again and again until the error come down as to other numbers.

例如-假设您是一名老师，您正在教孩子如何识别0–9位数字。 对于数字0、2、3、4、5、6、8、9，他可以获得70％的正确答案。 但是当他得到1位和7位数字时，他会变成50–50(他无法分辨)。 因为数字1和7与他相似。 因此，当您注意到这一点时，您便开始关注他所面临的大部分问题的1和7。 这种平衡在人类中是可能的，因为如果您一直问同样的问题，那么他最终会失败，他最终会变得沮丧，并且会放弃，但是神经网络却并非如此，因为NN没有感觉。 我们可以为这些错误反复训练网络，直到错误降到其他数值为止。

This is true that some people may have faced a situation where their teachers ask the same thing to their student where they keep failing and which makes them feel that their teacher wants to fail them. And that’s behavior is actually adverse behavior.

的确，有些人可能会遇到这样的情况，即他们的老师向他们的学生问同样的事情，而他们不断失败，这使他们感到自己的老师想让他们失败。 那实际上是不良行为。

How to make a similar scenario in neural networks? Actually, we can make an actual adverse network.

如何在神经网络中做出类似的场景？ 实际上，我们可以建立一个实际的不利网络。

If there is some process which genuinely doing its best to make neural network to give us high error as much as possible and produce this effect and if it spots any weakness then it focuses on that therefore it forces the learner to learn not to have that weakness anymore.

如果有某个过程能够真正尽其所能使神经网络尽可能多地给我们带来高误差并产生这种效果，并且发现了任何弱点，那么它就会着重于此，因此它迫使学习者学习没有那种弱点不再。

GAN(对抗性网络：- (GAN(Generative Adversarial Network: -)

GAN is consisting of two models / One is Discriminator an another is Generator. While training GAN both these networks literally compete with each other. Both these networks compete for the only parameter and that is the discriminator error rate. The generator adjusts its weight to produce a higher error and the Discriminator learns to try to lower the error. Let’s understand with the help of an example.

GAN由两种模型组成/一种是鉴别器，另一种是生成器。 在训练GAN时，这两个网络实际上相互竞争。 这两个网络都争夺唯一的参数，那就是鉴别器错误率。 生成器调整其权重以产生更高的误差，鉴别器学会设法降低误差。 让我们借助示例来理解。

范例：-(Example: -)

There is a forger who tries to make a fake painting to sell at a higher price. And there is one inspector to check the paintings to tell if a painting is fake or real.

有一个伪造者试图制造一幅假画，以更高的价格出售。 并且有一名检查员检查这些画作，以判断画是假的还是真实的。

So, initially, forger just draws some random lines on the paper and the inspector was like I hmm I am not sure. Because initially both Generator and Discrimination don’t have any learning.

因此，最初，forger只是在纸上画了一些随机的线，而检查员就像我不确定。 因为起初，生成器和歧视都没有任何知识。

Later forger painter learns more about different kinds of paint to make a painting that looks like the original painting and the inspector learns to the fined pattern to differentiate between fake and original painting. When Inspector looks at forgers newly generated painting then the inspector rejects it as it’s a fake and this process goes on. Eventually, a situation arises where Forger will make a picture that looks original, and Inspector tells that I am not sure whether is real or fake. In a neural network, terms Generate to produce a painting which looks like exactly original and Discriminator gives 0.5 as output which means discriminator is not able to differentiate between real and fake picture. At this point, we can chop off the Discriminator from the network to have a fully trained generator that can generate paintings that looks real.

后来，伪造画家更多地了解了不同种类的油漆，以制作出看起来像原始绘画的绘画，而检查员则学习了精细的图案，以区分假绘画和原始绘画。 当检查员查看伪造的新生成的绘画时，检查员将其视为伪造而拒绝，并且此过程继续进行。 最终，出现一种情况，Forger将制作一张看起来很原始的图片，而Inspector告诉我不确定是真实的还是伪造的。 在神经网络中，术语“生成”产生一幅看起来完全像原始的绘画，而“鉴别符”给出的输出为0.5，这意味着鉴别符无法区分真实图片和伪图片。 在这一点上，我们可以从网络上剔除“鉴别器”，以拥有一个经过全面培训的生成器，该生成器可以生成看起来真实的绘画。

There is more to this. If we feed lots of images of the car to the GAN network to generate a new car sample then one thing is sure that now GAN understands what is a car. Because the network will construct a structure which is also called a feature vector in latent space and these vectors are meaning full if we look at it. This latent space is a mapping to the input data distribution. And each dimension has meaning to particular features of the car. For example, if one axis in latent space belongs to the size of the car and another axis belongs to the color of the car.

还有更多。 如果我们将大量汽车图像提供给GAN网络以生成新的汽车样本，那么可以肯定的是，现在GAN可以理解什么是汽车了。 因为网络将在潜在空间中构造一个也称为特征向量的结构，如果我们看一下，这些向量就意味着充满。 该潜在空间是对输入数据分布的映射。 每个尺寸都对汽车的特定功能有意义。 例如，如果潜在空间中的一个轴属于汽车的大小，而另一个轴属于汽车的颜色。

So, if we move a data point in input distribution then there will be a very smooth transition in latent space also. And this causes the generation of a new unseen sample which is similar to input data distribution.

因此，如果我们在输入分布中移动数据点，则在潜在空间中也会有非常平滑的过渡。 这会导致生成一个新的看不见的样本，该样本类似于输入数据分布。