In this issue: 

• we introduce DCGANs;  

• we explain the DCGAN Paper;  

• we explore Nvidia Imaginaire, a GAN Library for image and video translation.  

Enjoy the learning!  

💡 ML Concept of the Day: What are DCGANs 

In the last part of our series about generative models, we have been exploring different types of adversarial neural networks (GANs). Today, we would like to discuss a popular variation of this architecture known as deep convolutional GAN (DCGAN). The ideas for DCGAN were outlined in a 2016 paper from researchers from Meta (then, Facebook) and big data startup Indico. The core thesis of the paper looked to ...