Generative Adversarial Networks

Generative Adversarial Networks (GANs) are a type of artificial intelligence algorithm which has two 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 two 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 math behind it
Tips and tricks – normalizing data, optimization, label smoothing and more
Challenges of training GANs – mode colapse, counting, perspective and Global Structure

 

Frameworks and tools covered: Python 3.5, Anaconda 5.0, NumPy 1.13, Matplotlib 2.1, Tensorflow 1.4, Keras 2.1

Your Courses, Your Way

All of our project-based courses are designed to be flexible – you can access courses 24/7 to fit them around your schedule, and choose the learning materials that suit you best.

You can even download your course videos and watch them offline using the Zenva app, available on iOS and Android.

Learn from World-Class Instructors