Generative Adversarial Networks
Write a Neural Network algorithm that will generate realistic photographs of objects, nature and human faces.
- 2.8 Hours of Video
- Certificate of Completion
- Source Code
- Closed Captions
- On-demand, 24/7 access
- 2.8 hours of video
- Certificate of completion
- Source code and PDF notes
- Closed captions
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 lessons and watch them offline using the Zenva app, available on iOS and Android.
Learn from World-Class Instructors
Our course instructors participate in elite developer programs and have been recognized for their demonstrated excellence in development and teaching.
That way, you can be confident that you’re learning the most up-to-date content from industry experts.
Interactive Lessons with Codemurai
Our unlimited access package comes with free access to all of the courses in our mobile app, Codemurai!
Available on iOS and Android, it’s full of interactive programming lessons and exercises so you can continue your learning on the go.
Achieve Real Results
Our community of 500,000+ learners and developers have used the skills learned with us to publish their own games and websites, land their dream jobs, and even start their own businesses – and you have the potential to do the same!
Check out what our learners think below:
“I love the lectures, concise course objectives, and how they not only teach you enough to get started, but prepare you for the advanced stuff later down the road.”
“With Zenva, I started learning a more accurate way to approach problems and develop solutions. It’s full of interesting topics that I love to learn in conjunction with my work.”
“I chose Zenva because of the large selection of topics and the fact that I can choose what courses I want to take whenever I want to take them. That level of freedom is unique to Zenva.”
“The Unity courses at Zenva helped me achieve a level of comfort with game development that I didn’t think was possible. They give you the confidence to expand your skills, and were so easy to understand.”
- Intermediate Python programming skills
- Familiarity with Artificial Neural Networks
- Familiarity with Convolutional Neural Networks
OR access ALL Zenva courses with our subscription.
- Access all 200+ courses
- New courses added monthly
- Cancel anytime
- Certificates of completion