Apply generative adversarial networks (GAN)

In this course you will learn: - Explore the application areas of GANs and consider them in terms of data augmentation, privacy, and anonymity - Use an image-to-image translation framework and identify its application in modalities other than images - Implement Pix2Pix, a pairwise image-to-image translation GAN, to adapt satellite imagery to mapping routes (and vice versa) - Compare pairwise image-to-image translation with unpaired image-to-image translation and identify how their key differences require different GAN architectures - Implement CycleGAN, an unpaired image-to-image translation model, to adapt horses to zebras (and vice versa) using two GANs in a single system The DeepLearning Generative Adversary Networks (GANs) in Artificial Intelligence specialization offers a fascinating introduction to image generation with GANs, leading the way from fundamental concepts to advanced techniques in an easy-to-understand approach. It also covers social implications, including bias in ML and how to detect it, privacy preservation, and more. Build a comprehensive knowledge base and gain hands-on experience with GANs. Train your own model using PyTorch, use it to generate images, and evaluate various advanced GANs. This specialization provides an accessible path for students of all levels who want to enter the GANs field or apply GANs to their own projects, even without prior exposure to advanced mathematics and machine learning research.