Download as pptx, pdf, or txt
Download as pptx, pdf, or txt
You are on page 1of 7

Generative Adversarial

Networks
(GAN)

-- Presentation By Aniket Srivastava


GAN ?
• GAN consists of two models that competes with each other to
analyze, capture and copy the variation within a given dataset.
Generator and Discriminator
• Generator = It learns to create fake data by incorporating feedback
from the discriminator
• Discriminator = It is a classifier that identifies real data from the fake
data created by the Generator
Working of GAN ?
• GAN consists of two networks, a Generator G(x) and a Discriminator
D(x)
• Uses Formula :
Types :
• Vanilla GANs
• Deep Convolutional GANs
• Conditional GANs
• Super Resolution GANs
Applications :
• Generating cartoon characters
• Generating real human faces
• Text to image translation
• 3 D Object Generations
• Gaming Applications
• Fake currency Detections
Thank You

Any query?
Please contact Aakansha Ma’am

You might also like