Generative Adversarial Network (GAN)

一、Basic Idea of GAN

Generation

We will control what to generate latter. → Conditional Generation

Algorithm

二、GAN as structured learning

Why Structured Learning Challenging?
One-shot/Zero-shot Learning:
In classification, each class has some examples.
In structured learning,
If you consider each possible output as a “class” ……
Since the output space is huge, most “classes” do not have any training data.
Machine has to create new stuff during testing.
Need more intelligence

Machine has to learn to do planning
Machine generates objects component-by-component, but it should have a big picture in its mind.
Because the output components have dependency, they should be considered globally.

三、Can Generator learn by itself?

It will be fine if the generator can truly copy the target image.
What if the generator makes some mistakes …….
Some mistakes are serious, while some are fine.


The relation between the components are critical.
Although highly correlated, they cannot influence each other.
Need deep structure to catch the relation between components.

四、Can Discriminator generate?

It is easier to catch the relation between the components by top-down evaluation.

Suppose we already have a good discriminator D(x) …

Discriminator - Training

In practice, you cannot decrease all the x other than real examples.

五、A little bit theory

总结