Review: GAN — Generative Adversarial Nets (GAN)

Generator and Discriminator Trained Together, Invented By Ian GoodFellows. By using GAN, we can synthesize some very realistic good samples.

Outline

1. GAN Value Function

Generative Adversarial Nets (GANs)
Two-player minimax game with value function V (D,G)

Since D(x) outputs the probability which ranges from 0 to 1, log of D(x) ranges from -ve infinity to 0.

When D guess correctly for real data, D(x) close to 1, log D(x) close to 0 which can maximize the function above.

When D guess correctly for fake data, D(G(z)) close to 0, log (1-D(G(z))) close to 0 which can maximize the function above.

The objective of G is to generate samples such that D cannot distinguish whether it is real or fake data, and finally D can only have a random guess of 1/2.

2. GAN Conceptual Idea

Conceptual Idea

3. GAN Algorithm

GAN Algorithm

4. GAN Results

Samples from the model a) MINIST, b) TFD, c) CIFAR-10 fully connected model, d) CIFAR-10 convolutional D and deconvolutional G (Rightmost are the nearest training example of the neighboring samples)

Reference

My Previous Reviews

--

--

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store