What you'll learn:
- GAN's Topic Overview and Prerequisites
- Theoretical Concept behind GAN's
- KL & JS Divergence
- Underlying math behind GAN's : Min - Max Game
- DCGAN & Hands on Python
- Conditional GAN & Hands on Python
- ACGAN & Hands on Python
- Challenges in training the GAN's
- Evaluation metrics & Tips for making GAN'S in real life
- Practical Application - Synthetic class specific image generation using GANs
- Some other cool applications of GAN's
- Semi-supervised learning with Generative Adversarial Networks
- Hands on Semi-supervised learning with Generative Adversarial Network
- Summary & additional resources
In this course, you will:
- Learn about GANs and their applications
- Understand the intuition behind the fundamental components of GANs
- Explore and implement multiple GAN architectures
- Build conditional GANs &ACGAN's capable of generating examples from determined categories.
This Generative Adversarial Networks (GANs) Specialization provides an exciting introduction to image generation with GANs, charting a path from foundational concepts to advanced techniques through an easy-to-understand approach.
It also covers social implications, including bias in ML and the ways to detect it, privacy preservation, and more.
Build a comprehensive knowledge base and gain hands-on experience in GANs with the most loved language:Python.
Train your own model using Tensorflow &Keras, use it to create images, and evaluate a variety of advanced GANs.
This Specialization provides an accessible pathway for an intermediate level of learners looking to break into the GANs space or apply GANs to their own projects, even without prior familiarity with advanced math and machine learning research.
