no code implementations • 25 Oct 2023 • Lisa Schut, Nenad Tomasev, Tom McGrath, Demis Hassabis, Ulrich Paquet, Been Kim
Artificial Intelligence (AI) systems have made remarkable progress, attaining super-human performance across various domains.
1 code implementation • 13 Dec 2021 • Elizabeth Bondi, Raphael Koster, Hannah Sheahan, Martin Chadwick, Yoram Bachrach, Taylan Cemgil, Ulrich Paquet, Krishnamurthy Dvijotham
Using real-world conservation data and a selective prediction system that improves expected accuracy over that of the human or AI system working individually, we show that this messaging has a significant impact on the accuracy of human judgements.
no code implementations • 17 Nov 2021 • Thomas McGrath, Andrei Kapishnikov, Nenad Tomašev, Adam Pearce, Demis Hassabis, Been Kim, Ulrich Paquet, Vladimir Kramnik
In this work we provide evidence that human knowledge is acquired by the AlphaZero neural network as it trains on the game of chess.
2 code implementations • 9 Sep 2020 • Nenad Tomašev, Ulrich Paquet, Demis Hassabis, Vladimir Kramnik
We compare nine other variants that involve atomic changes to the rules of chess.
no code implementations • 20 Jul 2019 • Silvia Chiappa, Ulrich Paquet
We present an approach to learn the dynamics of multiple objects from image sequences in an unsupervised way.
no code implementations • 18 Dec 2018 • Ulrich Paquet, Sumedh K. Ghaisas, Olivier Tieleman
We assume that a high-dimensional datum, like an image, is a compositional expression of a set of properties, with a complicated non-linear relationship between the datum and its properties.
no code implementations • 28 Oct 2018 • Ulrich Paquet, Marco Fraccaro
This technical report presents pseudo-code for a Riemannian manifold Hamiltonian Monte Carlo (RMHMC) method to efficiently simulate samples from $N$-dimensional posterior distributions $p(x|y)$, where $x \in R^N$ is drawn from a Gaussian Process (GP) prior, and observations $y_n$ are independent given $x_n$.
1 code implementation • ICLR 2018 • Rasmus Berg Palm, Ulrich Paquet, Ole Winther
Humans possess an ability to abstractly reason about objects and their interactions, an ability not shared with state-of-the-art deep learning models.
6 code implementations • NeurIPS 2018 • Rasmus Berg Palm, Ulrich Paquet, Ole Winther
We achieve state of the art results on the bAbI textual question-answering dataset with the recurrent relational network, consistently solving 20/20 tasks.
Ranked #3 on Question Answering on bAbi (Mean Error Rate metric)
1 code implementation • NeurIPS 2017 • Marco Fraccaro, Simon Kamronn, Ulrich Paquet, Ole Winther
This paper takes a step towards temporal reasoning in a dynamically changing video, not in the pixel space that constitutes its frames, but in a latent space that describes the non-linear dynamics of the objects in its world.
no code implementations • 15 Aug 2016 • Mike Gartrell, Ulrich Paquet, Noam Koenigstein
Determinantal point processes (DPPs) are an elegant model for encoding probabilities over subsets, such as shopping baskets, of a ground set, such as an item catalog.
1 code implementation • NeurIPS 2016 • Marco Fraccaro, Søren Kaae Sønderby, Ulrich Paquet, Ole Winther
How can we efficiently propagate uncertainty in a latent state representation with recurrent neural networks?
no code implementations • 7 Apr 2016 • Marco Fraccaro, Ulrich Paquet, Ole Winther
The estimation of normalizing constants is a fundamental step in probabilistic model comparison.
1 code implementation • 17 Feb 2016 • Mike Gartrell, Ulrich Paquet, Noam Koenigstein
In this work we present a new method for learning the DPP kernel from observed data using a low-rank factorization of this kernel.
no code implementations • 16 Jul 2015 • Ulrich Paquet
We highlight a pitfall when applying stochastic variational inference to general Bayesian networks.
no code implementations • 9 Sep 2014 • Ulrich Paquet, Noam Koenigstein, Ole Winther
We present a novel, scalable and Bayesian approach to modelling the occurrence of pairs of symbols (i, j) drawn from a large vocabulary.
no code implementations • 26 Sep 2013 • Ulrich Paquet, Noam Koenigstein
The bane of one-class collaborative filtering is interpreting and modelling the latent signal from the missing class.
no code implementations • 12 Jan 2013 • Manfred Opper, Ulrich Paquet, Ole Winther
A perturbative expansion is made of the exact but intractable correction, and can be applied to the model's partition function and other moments of interest.
no code implementations • NeurIPS 2008 • Manfred Opper, Ulrich Paquet, Ole Winther
We develop as series of corrections to Expectation Propagation (EP), which is one of the most popular methods for approximate probabilistic inference.