Search results
Biography. Zoubin Ghahramani FRS is Professor of Information Engineering at the University of Cambridge, a Fellow of St John's College, former Chief Scientist at Uber, and currently a Distinguished Researcher at Google AI.
We would like to show you a description here but the site won’t allow us.
Jun 6, 2015 · In this paper we develop a new theoretical framework casting dropout training in deep neural networks (NNs) as approximate Bayesian inference in deep Gaussian processes. A direct result of this theory gives us tools to model uncertainty with dropout NNs -- extracting information from existing models that has been thrown away so far.
Semantic Scholar profile for Zoubin Ghahramani, with 7147 highly influential citations and 425 scientific research papers.
Jul 30, 2021 · Professor Zoubin Ghahramani. In an announcement made today (30 July) by UK Research and Innovation (UKRI), five internationally recognised researchers, including Professor Ghahramani, were named as the new fellows, as part of the UK's commitment to further strengthen its position as a global leader in the AI field.
Zoubin Ghahramani. I studied Computer Science and Cognitive Science at the University of Pennsylvania and obtained my PhD from MIT in 1995. From 1995 to 1998, I was a Postdoctoral Fellow at the University of Toronto, working with Geoff Hinton. I was one of the founding faculty members of the Gatsby Computational Neuroscience Unit at UCL (1998 ...
Zoubin Ghahramani, Yoshua Bengio, + 1. NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems • December 2018, pp 2371-2380. In this paper, we propose a conceptually simple and general framework called MetaGAN for few-shot learning problems.
