Search results
Liked by Zoubin Ghahramani. Location: United Kingdom · 500+ connections on LinkedIn. View Zoubin Ghahramani’s profile on LinkedIn, a professional community of 1 billion members.
May 28, 2015 · Probabilistic modelling provides a framework for understanding what learning is, and has therefore emerged as one of the principal theoretical and practical approaches for designing machines that learn from data acquired through experience. The probabilistic framework, which describes how to represent and manipulate uncertainty about models and ...
Semantic Scholar profile for Zoubin Ghahramani, with 7147 highly influential citations and 425 scientific research papers.
Dec 16, 2015 · A Theoretically Grounded Application of Dropout in Recurrent Neural Networks. Yarin Gal, Zoubin Ghahramani. Recurrent neural networks (RNNs) stand at the forefront of many recent developments in deep learning. Yet a major difficulty with these models is their tendency to overfit, with dropout shown to fail when applied to recurrent layers.
CoRR abs/1706.00387 ( 2017) [i42] Matej Balog, Nilesh Tripuraneni, Zoubin Ghahramani, Adrian Weller: Lost Relatives of the Gumbel Trick. CoRR abs/1706.04161 ( 2017) [i41] Jordan Burgess, James Robert Lloyd, Zoubin Ghahramani: One-Shot Learning in Discriminative Neural Networks. CoRR abs/1707.05562 ( 2017)
Zoubin Ghahramani, Chief Scientist at Uber, understands that movement requires intelligence, and draws a parallel between biological and artificial systems. ...
- 2 min
- 11.9K
- Uber Engineering
Jun 6, 2015 · Convolutional neural networks (CNNs) work well on large datasets. But labelled data is hard to collect, and in some applications larger amounts of data are not available. The problem then is how to use CNNs with small data -- as CNNs overfit quickly. We present an efficient Bayesian CNN, offering better robustness to over-fitting on small data than traditional approaches. This is by placing a ...
