Beyond Supervised Deep Learning
Deep learning has transformed the way in which we design machine learning systems. In this talk I will provide a brief overview of modern advances to the deep learning paradigm. Starting off with deep reinforcement learning: DQN (Nature, 2015) and A3C (CoRR, 2015), I will then motivate the role of generative modelling in the emerging research landscape and discuss several recent models, including Pixel CNNs (ICML, 2016), AIR (NIPS, 2016) and Conditional 2D->3D (NIPS, 2016).
Ali Eslami is a research scientist at Google DeepMind in London. Previously, he was a post-doctoral researcher at Microsoft Research in Cambridge. He did his PhD in the School of Informatics at the University of Edinburgh, during which he was also a visiting researcher in the Visual Geometry Group at the University of Oxford.
Download presentation from here.
Watch video from here.