Browsing CBMM Memo Series by Subject "Encoder-Recurrent-Decoder framework"
Now showing items 1-1 of 1
-
UNSUPERVISED LEARNING OF VISUAL STRUCTURE USING PREDICTIVE GENERATIVE NETWORKS
(Center for Brains, Minds and Machines (CBMM), arXiv, 2015-12-15)The ability to predict future states of the environment is a central pillar of intelligence. At its core, effective prediction requires an internal model of the world and an understanding of the rules by which the world ...