Paper overview | Unsupervised Learning of Visual Structure Using Predictive Generative Networks
Article overview: Unsupervised Learning of Visual Structure Using Predictive Generative Networks from Ilya Kuzovkin
This set of slides goes over the recent article that tries to tie together the idea of predictive coding and deep learning. The main point of the article is that a generative system trained on sequential data to predict the future samples learns more “useful” representation than the usual autoencoder. The result resonates with the fact that our brain is probably using predictive mechanisms.
No comments yet.