Generative Adversarial Networks
A Generative Adversarial Network (GAN) is a type of unsupervised deep learning system that is implemented as two competing neural networks. One network, the generator, creates fake data that looks exactly like the real data set. The second network, the discriminator, ingests real and synthetic data. Over time, each network improves, enabling the pair to learn the entire distribution of the given data set.
Comparison of Generative Adversarial Networks (GAN) and CNN
If GAN is compared to CNN than it outclass CNN because GAN has generation capability and it can work with unlabeled data because it belongs to unsupervised learning techniques.
Generative Adversarial Networks Uses
GANs open up deep learning to a broader range of unsupervised tasks in which labeled data does not exist or is too expensive to obtain. They also reduce the load required for a deep neural network because the two systems share the burden. Expect to see more business applications, such as cyber detection, employ GANs.