no code implementations • ICLR 2019 • Tiago Ramalho, Tomas Kocisky, Frederic Besse, S. M. Ali Eslami, Gabor Melis, Fabio Viola, Phil Blunsom, Karl Moritz Hermann
Natural language processing has made significant inroads into learning the semantics of words through distributional approaches, however representations learnt via these methods fail to capture certain kinds of information implicit in the real world.
no code implementations • 3 Oct 2019 • Tiago Ramalho, Thierry Sousbie, Stefano Peluchetti
Recent algorithms with state-of-the-art few-shot classification results start their procedure by computing data features output by a large pretrained model.
no code implementations • 20 Aug 2019 • Tiago Ramalho, Miguel Miranda
Deep learning models frequently make incorrect predictions with high confidence when presented with test examples that are not well represented in their training dataset.
1 code implementation • ICLR 2019 • Tiago Ramalho, Marta Garnelo
The ability to generalize quickly from few observations is crucial for intelligent systems.
1 code implementation • 4 Jul 2018 • Tiago Ramalho, Tomáš Kočiský, Frederic Besse, S. M. Ali Eslami, Gábor Melis, Fabio Viola, Phil Blunsom, Karl Moritz Hermann
Natural language processing has made significant inroads into learning the semantics of words through distributional approaches, however representations learnt via these methods fail to capture certain kinds of information implicit in the real world.
17 code implementations • ICML 2018 • Marta Garnelo, Dan Rosenbaum, Chris J. Maddison, Tiago Ramalho, David Saxton, Murray Shanahan, Yee Whye Teh, Danilo J. Rezende, S. M. Ali Eslami
Deep neural networks excel at function approximation, yet they are typically trained from scratch for each new function.
24 code implementations • 2 Dec 2016 • James Kirkpatrick, Razvan Pascanu, Neil Rabinowitz, Joel Veness, Guillaume Desjardins, Andrei A. Rusu, Kieran Milan, John Quan, Tiago Ramalho, Agnieszka Grabska-Barwinska, Demis Hassabis, Claudia Clopath, Dharshan Kumaran, Raia Hadsell
The ability to learn tasks in a sequential fashion is crucial to the development of artificial intelligence.
Ranked #3 on Continual Learning on F-CelebA (10 tasks)