Published in

Generative Adversal Networks in Machine Learning

GANs is one of the helpful techniques from Machine Learning related to photo editing.

A Generative Adversarial Network also known as — GAN is a group of Machine Learning. It was designed by Ian Goodfellow and his colleagues in 2014. Initially, they were put forward as a generative model for unsupervised learning but they are being extremely useful for semisupervised learning, supervised learning, and also for reinforcement learning. They are created with the help of two neural networks that compete with each other and have the ability to create new output by analyzing, capturing, and copying the variation from the given datasets. Basically, this technique has the ability to create new data sets of the same statistics as the training sets. Hence it is quite popular among AI Startups and their different products.

Working of Generative Adversarial Network

In GAN we have a generator and a discriminator. Basically here both of them are neural networks and also as we have seen that they compete with each other in the training phase. Here the generator tries to mislead the discriminator by forging the data samples. But the discriminator tries to differentiate between the real and forged samples. And after a number of repetitions of the steps, they both start getting better with each step. improve

Basically, GANs are said to be minimax games because of their behavior of competing with each other. Here discriminator works to minimize its rewards V(D, G) and the generator on the other hand tries to minimize the discriminator’s awards.

The mathematical representation of GANs is,

Types of Generative Adversal Networks

There are a number of Generative Adversal Networks developed and implemented in recent years. We shall be looking at a few of them,

  • Laplacian PYramid Gan (LAPGAN)
  • Vanilla GAN
  • Deep Convolutional GAN (DCGAN)
  • Super Resolution GAN( SRGAN)
  • Conditional GAN (CGAN)

Hence we can conclude that the application of GANs and their techniques to generate realistic photographs, to go text to image translation, generate images of data sets, etc are extremely helpful and popular. Here we have seen a few of them. Hence they are one of the popular and useful techniques in machine learning.



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