Search Results - "Paquet, Ulrich"

Acquisition of chess knowledge in AlphaZero by McGrath, Thomas, Kapishnikov, Andrei, Tomašev, Nenad, Pearce, Adam, Wattenberg, Martin, Hassabis, Demis, Kim, Been, Paquet, Ulrich, Kramnik, Vladimir

“…We analyze the knowledge acquired by AlphaZero, a neural network engine that learns chess solely by playing against itself yet becomes capable of outperforming…”
Get full text

Unsupervised separation of dynamics from pixels by Chiappa, Silvia, Paquet, Ulrich

“…We present an approach to learn the dynamics of multiple objects from image sequences in an unsupervised way. We introduce a probabilistic model that first…”
Get full text

Efficient Bayesian inference of instantaneous reproduction numbers at fine spatial scales, with an application to mapping and nowcasting the Covid‐19 epidemic in British local authorities by Teh, Yee Whye, Elesedy, Bryn, He, Bobby, Hutchinson, Michael, Zaidi, Sheheryar, Bhoopchand, Avishkar, Paquet, Ulrich, Tomasev, Nenad, Read, Jonathan, Diggle, Peter J.

Get full text

A hierarchical model for ordinal matrix factorization by Paquet, Ulrich, Thomson, Blaise, Winther, Ole

“…This paper proposes a hierarchical probabilistic model for ordinal matrix factorization. Unlike previous approaches, we model the ordinal nature of the data…”
Get full text

Authors' reply to the discussion of ‘Efficient Bayesian Inference of Instantaneous Reproduction Numbers at Fine Spatial Scales, with an Application to Mapping and Nowcasting the Covid‐19 Epidemic in British Local Authorities’ by Teh et al. in Session 2 of the Royal Statistical Society's Special Topic Meeting on COVID‐19 transmission: 11 June 2021 by Teh, Yee Whye, Elesedy, Bryn, He, Bobby, Hutchinson, Michael, Zaidi, Sheheryar, Bhoopchand, Avishkar, Paquet, Ulrich, Tomasev, Ne‐nad, Read, Jonathan, Diggle, Peter J.

Get full text

Correlating Variational Autoencoders Natively For Multi-View Imputation by Orme, Ella S. C, Evangelou, Marina, Paquet, Ulrich

“…Multi-view data from the same source often exhibit correlation. This is mirrored in correlation between the latent spaces of separate variational autoencoders…”
Get full text

Unsupervised Separation of Dynamics from Pixels by Chiappa, Silvia, Paquet, Ulrich

“…METRON, Springer, 2019 We present an approach to learn the dynamics of multiple objects from image sequences in an unsupervised way. We introduce a…”
Get full text

An Efficient Implementation of Riemannian Manifold Hamiltonian Monte Carlo for Gaussian Process Models by Paquet, Ulrich, Fraccaro, Marco

“…This technical report presents pseudo-code for a Riemannian manifold Hamiltonian Monte Carlo (RMHMC) method to efficiently simulate samples from…”
Get full text

On the Convergence of Stochastic Variational Inference in Bayesian Networks by Paquet, Ulrich

“…We highlight a pitfall when applying stochastic variational inference to general Bayesian networks. For global random variables approximated by an exponential…”
Get full text

Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero by Schut, Lisa, Tomasev, Nenad, McGrath, Tom, Hassabis, Demis, Paquet, Ulrich, Kim, Been

“…Artificial Intelligence (AI) systems have made remarkable progress, attaining super-human performance across various domains. This presents us with an…”
Get full text

Gaussian process modeling for image distortion correction in echo planar imaging by Stevick, Joseph W., Harding, Sally G., Paquet, Ulrich, Ansorge, Richard E., Carpenter, T. Adrian, Williams, Guy B.

“…An enhanced method for correction of image distortion due to B0‐field inhomogeneities in echo planar imaging (EPI) is presented. The algorithm is based on the…”
Get full text

Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess by Tomašev, Nenad, Paquet, Ulrich, Hassabis, Demis, Kramnik, Vladimir

“…It is non-trivial to design engaging and balanced sets of game rules. Modern chess has evolved over centuries, but without a similar recourse to history, the…”
Get full text

A Factorial Mixture Prior for Compositional Deep Generative Models by Paquet, Ulrich, Ghaisas, Sumedh K, Tieleman, Olivier

“…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…”
Get full text

Role of Human-AI Interaction in Selective Prediction by Bondi, Elizabeth, Koster, Raphael, Sheahan, Hannah, Chadwick, Martin, Bachrach, Yoram, Cemgil, Taylan, Paquet, Ulrich, Dvijotham, Krishnamurthy

“…Recent work has shown the potential benefit of selective prediction systems that can learn to defer to a human when the predictions of the AI are unreliable,…”
Get full text

Acquisition of Chess Knowledge in AlphaZero by McGrath, Thomas, Kapishnikov, Andrei, Tomašev, Nenad, Pearce, Adam, Hassabis, Demis, Kim, Been, Paquet, Ulrich, Kramnik, Vladimir

“…What is learned by sophisticated neural network agents such as AlphaZero? This question is of both scientific and practical interest. If the representations of…”
Get full text

Recurrent Relational Networks by Palm, Rasmus Berg, Paquet, Ulrich, Winther, Ole

“…This paper is concerned with learning to solve tasks that require a chain of interdependent steps of relational inference, like answering complex questions…”
Get full text

One-class Collaborative Filtering with Random Graphs: Annotated Version by Paquet, Ulrich, Koenigstein, Noam

“…The bane of one-class collaborative filtering is interpreting and modelling the latent signal from the missing class. In this paper we present a novel Bayesian…”
Get full text

The Bayesian Low-Rank Determinantal Point Process Mixture Model by Gartrell, Mike, Paquet, Ulrich, Koenigstein, Noam

“…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…”
Get full text

An Adaptive Resample-Move Algorithm for Estimating Normalizing Constants by Fraccaro, Marco, Paquet, Ulrich, Winther, Ole

“…The estimation of normalizing constants is a fundamental step in probabilistic model comparison. Sequential Monte Carlo methods may be used for this task and…”
Get full text