general adversarial networks

general adversarial networks 

There are many ways a machine can be taught to generate an output on unseen data. The technological advancement in different sectors has left everyone shocked. we are now at a point where deep learning and neural networks are so powerful that can generate a new human face from scratch that does not exist before but looks real based on some trained data. 

The technique is none other than

GAN - ( Generative – To learn a generative model, which describes how data is generated in terms of a probabilistic model. In simple words, it explains how data is generated visually.

Adversarial – The training of the model is done in an adversarial setting.

Networks – use deep neural networks for training purposes.

Applications of Generative Adversarial Network 

Image to Image Translation – We can translate one Image to another without changing the background of the source image.

Low resolution to High resolution – If you pass a low-resolution Image or video, GAN can produce a high-resolution Image version of the same.

Prediction of Next Frame in the video – By training a neural network on small frames of video, GANs are capable to generate or predict a small next frame of video.

Interactive Image Generation – It means that GANs are capable to generate images and video footage in an art form if they are trained on the right real dataset.

Speech – Researchers from the College of London recently published a system called GAN-TTS that learns to generate raw audio through training on 567 corpora of speech data.

Component of Generative Adversarial Network

Discriminator - it is a supervised approach means It is a simple classifier that predicts data is fake or real. It is trained on real data and provides feedback to a generator.

Generator - it is an unsupervised learning approach. It will generate data that is fake data based on original(real) data. It is also a neural network that has hidden layers, activation, loss function. Its aim is to generate the fake image based on feedback and make the discriminator fool that it cannot predict a fake image. And when the discriminator is made a fool by the generator, the training stops and we can say that a generalized GAN model is created.

Different types of Generative Adversarial Network

DC GAN - it is a Deep convolutional GAN. It is one of the most used, powerful, and successful types of GAN architecture. 

Conditional GAN and un Conditional GAN (CGAN) - Conditional GAN is deep learning neural network in which some additional parameters are used.

Least square GAN ( LSGAN) - it is a type of GAN that adopts the least-square loss function for the discriminator.

Auxiliary classifier GAN (ACGAN) - It is the same as CGAN and an advanced version of it. 

Dual Video Discriminator GAN - DVD-GAN is a generative adversarial network for video generation built upon the BigGAN architecture.

SRGAN - Its main function is to transform low resolution to high resolution known as Domain Transformation.

Cycle GAN - it released in 2017 which performs the task of Image Translation. 

Info GAN - Advance version of GAN which is capable to learn to disentangle representation in an unsupervised learning approach.