Skip to main content

Intro to Generative Adversarial Networks | GANs 001

   GANs consist of three terms Generative Adversarial Network. Let's understand these three terms first. Generative : A Generative Model takes input training sample from some distribution and learns to represents that distribution. Adversarial : It basically means Conflicting or Opposing. Networks : These are basically neural networks. So,Generative Adversarial Networks are deep neural network architecture comprising of two neural networks compete with each other to make a generative model. A GAN consist of two class models : Discriminative Model :- It is the one that discriminate between two different classes of data.It tries to identify real data from fakes created by the generator Generative Model :- The Generator turns noise into an imitation of the data to try to trick the discriminator Mathematically, A Generative Model 'G' to be trained on training data 'X' sampled from some true distribution 'D' is the one which, given some standard random distrib...

Intro to Generative Adversarial Networks | GANs 001


 

 GANs consist of three terms Generative Adversarial Network. Let's understand these three terms first.

Generative : A Generative Model takes input training sample from some distribution and learns to represents that distribution.

Adversarial : It basically means Conflicting or Opposing.

Networks : These are basically neural networks.

So,Generative Adversarial Networks are deep neural network architecture comprising of two neural networks compete with each other to make a generative model.

A GAN consist of two class models :

  • Discriminative Model :- It is the one that discriminate between two different classes of data.It tries to identify real data from fakes created by the generator
  • Generative Model :- The Generator turns noise into an imitation of the data to try to trick the discriminator

Mathematically,

A Generative Model 'G' to be trained on training data 'X' sampled from some true distribution 'D' is the one which, given some standard random distribution 'z' produces a distribution 'd' which is close to 'D' according to some closeness metric.

 

 Intuition Behind GANs  

  • Generator starts from noise to try to create an imitation of the data. 
  • Discriminator looks at both real data and fake data created by the Generator
  • Discriminator tries to predict what's real and what's fake.
  • Generator tries to improve its imitation of the data using Back propogation
  • Discriminator tries to identify real data from fakes created by the generator
  • After training Generator network is used to create new data that's never been seen before. 


Comments

Popular posts from this blog

Best Platforms to Improve Machine Learning Skills | 2020

 Machine learning is one of the most exciting techniques one has ever encountered.The field of study that gives computers the ability to learn without being explicitly programmed is machine learning.Their are platforms that can help you improve your Machine Learning skills. Today I've come up with the list of some of my favorite platforms.   Platforms to Improve Machine Learning Skills 1. Kaggle The online community of data scientists and machine learning practitioners is Kaggle, a subsidiary of Google LLC. Kaggle is the largest data science community in the world.Kaggle enables users in a web-based data-science environment to find and publish data sets, explore and build models, work with other data scientists and machine learning engineers, and enter competitions to solve challenges in data science.With it's free GPUs, high paying competitions,massive community , thousands on datasets and notebooks, this platform helps a lot. 2. Seedbank It was launched by  'TensorFlow...