GAN is the most interesting idea

Fig.1- Generative Adversial Networks[1].

Generative Adversarial Networks (GANs) are neural nets which were first introduced by Ian Goodfellow in 2014. In GAN, two models are simultaneously trained: a generative model G that captures the data distribution, and a discriminative model D that estimates the probability that a sample came from the training data rather than G.




[2]: Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A. and Bengio, Y., 2014. Generative adversarial nets. In Advances in neural information processing systems (pp. 2672-2680).