Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks

arxiv.org

An older paper that deserves renewed attention. It introduces deep convolutional generative adversarial networks, which Yann LeCun mentioned as most promising research area of deep learning in the future. Most excitingly, this technique opens up the opportunity for unsupervised learning, hopefully obsolescing the need for laboriously annotated data sets. 

Read more...
Linkedin

Want to receive more content like this in your inbox?