This (GANs), and the variations that are now being proposed is the most interesting idea in the last 10 years in ML, in my opinion

GANs are one of the latest wonders of Deep Learning. These are capable of generating wisdom from garbage data. They can be used for generating images, videos, alter images and much more! The recent research in GANs is focused on generating Deep Fakes (of humans) and detecting them. GAN is essentially a neural network architecture (more of a framework than an architecture), wherein a generative model is paired with a non-generative model; the generative model is penalized for a bad quality generation, whereas, the other model is penalized for a good quality generation by the generative model. So in a way, these models compete to achieve their individual goals. The original paper suggests,

Generative Adversarial Networks (GANs) are nothing but a framework for estimating generative models via adversarial process.

In this article, we will see, what exactly GANs are, how they work and glance through a few use cases of it. Let’s take a peek into the main contents:

Contents

1. Generative v/s Discriminative Modeling
2. The Generative Adversarial Nature
3. A Few Use Cases (to get you thinking)
4. Conclusion

#deep-learning #artificial-intelligence #neural-networks #data-science