Ali Eslami
Tue 21 Feb 2017, 11:00 - 12:00
IF 4.31/4.33

If you have a question about this talk, please contact: Gareth Beedham (gbeedham)

"Scene Understanding Without Labels"




Deep learning has transformed the way in which we design machine learning systems. In this talk I will motivate the role of generative modeling in the emerging research landscape and discuss several recent applications to unsupervised scene understanding, including Conceptual Compression (NIPS, 2016), Attend-Infer-Repeat (NIPS, 2016) and Conditional 2D->3D (NIPS, 2016).


Conceptual Compression:


Conditional 2D->3D:




S. M. Ali Eslami is a research scientist at Google DeepMind working on problems related to artificial intelligence. Prior to that, 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. From 2012-2015 he helped organise the PASCAL Visual Object Classes challenge. His research is focused on getting computers to learn generative models of images that not only produce good samples but also good explanations for their observations.