Generative Adversarial Networks

Generative Adversarial Networks

Write a Neural Network algorithm that will generate realistic photographs of objects, nature and human faces!

$50

$50
Includes:
  • 16 Lessons
  • Lifetime, 24/7 Access
  • Certificate of Completion
Join 300,000+ Satisfied Students
$50

Overview

This title is part of the Deep Learning Mini-Degree

Generative Adversarial Networks (GANs) are a type of artificial intelligence algorithm, which has 2 different Neural Networks compete against each to gain knowledge. Introduced in 2014 by Ian Goodfellow, this technique can be successfully used to generate realistic photographs of objects, nature and even human faces. Other applications include removing noise from astrophysical images, generating new fake data for other neural networks, or even enhancing photos. You know how in movies, the FBI always does that cool zoom on a photo of a suspect? GANs can be used to actually do that!

This course begins with the basics and intuition of GANs, introducing the the 2 types of Models – Discriminative and Generative  – and their specific tasks in the algorithm. Continuing through this course, you’ll learn the difference between regular GANs, DCGANs (Deep Convolutional GANs) and AC-GANs (Auxiliary Classifer GANs), and how to implement them using Python.

What you’ll learn:

  • Classifying the data as real or artificially generated through a Discriminator 
  • Fooling the Discriminator into believing generated data is real via a Generator
  • Analyzing the problem using Game Theory
  • Training  a GAN – including an intuition of the algorithm and the maths behind it
  • Tips and tricks – normalizing data, optimization, label smoothing and more
  • Challenges of training GANs – mode colapse, counting, perspective and Global Structure

About the Deep Learning Mini-Degree 

The Deep Learning Mini-Degree is an on-demand learning curriculum composed of 6 professional-grade courses geared towards teaching you how to solve real-world problems and build innovative projects using Machine Learning and Python. Learn and understand the fundamentals necessary to build the next generation of intelligent applications and software, with concepts and theory that can be applied across technology and frameworks.

Challenge yourself by joining this exciting project-based curriculum and gain the knowledge and abilities required to succeed in this brand new industry. No prior experience with AI or Machine Learning is necessary to join. However, basic to intermediate Python skills are assumed in all of the courses.

https://www.youtube.com/watch?v=pcahHKBBMGo

 

+ Show More

What Our Members Are Saying

“I was able to just continuously expand upon the groundwork that I created with the course and turn it into something that was uniquely mine.”
Damon Bolesta

“Zenva courses are not like other similar courses ... I found them more friendly and interesting than other sites I’d tried.”
Elizaveta Mihisa

“Once I actually started to type, a giant game programming world opened up before my eyes and it is absolutely amazing!”
Ryan Mininger

“This course definitely helped me create my first game for Android and iOS — which is a very good feeling 😀 — so I highly recommend it!”
Max Rose

Curriculum

+ Show More

Requirements

  • Intermediate Python programming skills
  • Familiarity with Artificial Neural Networks
  • Familiarity with Convolutional Neural Networks

SIGNUP