What is the primary objective of the discriminator in a GAN during training? 单项选择题

A

To minimize the probability of real data being real.

B

To maximize the probability of real data being real and minimize the probability of fake data being real.

C

To generate data samples that resemble the training data.

登录即可查看完整答案

我们收录了全球超50000道真实原题与详细解析,现在登录,立即获得答案。

类似问题

Which statement about Generative Adversarial Networks (GANs) is TRUE?

在我们学习过的基本生成对抗网络 (GAN) 中，有一个“生成器网络”。 生成器网络的目标是什么？ （种子/随机 z 是一个叫做生成器网络  G(*) 模型的输入，产生生成/假样本 G(z)。  生成/假样本 G(z) 然后作为判别器网络 D(*) 的输入。同时，真实数据样本 x 也作为判别器网络 D(*) 的输入。  判别器网络 D(*) 判断它是真的还是假的。）   In the basic Generative Adversarial Network (GAN) we studied in one of the lectures (as illustrated below), there is “Generator Network”. What is the goal of the Generator Network?   (There is Seed/Random z which is an input to the a model called Generator Network G(*) which generates Generated/Fake Sample G(Z). The Generated/Fake Sample G(Z) is then an input to the Discriminator Network D(*). Along with this, Real Data Sample x is also an input to the Discriminator Network D(*). The Discriminator Network D(*) then results in whether it is Real or Fake.)

Reference Figure 1. Typically early in training, the value of D(G(z)) is closer to which of the following values?

Reference Figure 1. You know that your GAN is trained when D(G(z)) is close to 1

更多留学生实用工具

加入我们，立即解锁 海量真题 与 独家解析，让复习快人一步！