User profiles for Nando de Freitas

Nando de Freitas

CIFAR & DeepMind
Verified email at google.com
Cited by 70449

Taking the human out of the loop: A review of Bayesian optimization

…, Z Wang, RP Adams, N De Freitas - Proceedings of the …, 2015 - ieeexplore.ieee.org
Big Data applications are typically associated with systems involving large numbers of users,
massive complex software systems, and large-scale heterogeneous computing and …

[PDF][PDF] On autoencoders and score matching for energy based models

…, MA Ranzato, D Buchman, ND Freitas… - Proceedings of the …, 2011 - cs.toronto.edu
We consider estimation methods for the class of continuous-data energy based models (EBMs).
Our main result shows that estimating the parameters of an EBM using score matching …

An introduction to MCMC for machine learning

C Andrieu, N De Freitas, A Doucet, MI Jordan - Machine learning, 2003 - Springer
This purpose of this introductory paper is threefold. First, it introduces the Monte Carlo method
with emphasis on probabilistic machine learning. Second, it reviews the main building …

A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning

E Brochu, VM Cora, N De Freitas - arXiv preprint arXiv:1012.2599, 2010 - arxiv.org
We present a tutorial on Bayesian optimization, a method of finding the maximum of expensive
cost functions. Bayesian optimization employs the Bayesian technique of setting a prior …

Matching words and pictures

K Barnard, P Duygulu, D Forsyth, N Freitas… - Journal of machine …, 2003 - jmlr.org
We present a new approach for modeling multi-modal data sets, focusing on the specific case
of segmented images with associated text. Learning the joint distribution of image regions …

[BOOK][B] Sequential Monte Carlo methods in practice

A Doucet, N De Freitas, NJ Gordon - 2001 - Springer
Monte Carlo methods are revolutionising the on-line analysis of data in fields as diverse as
financial modelling, target tracking and computer vision. These methods, appearing under …

The unscented particle filter

…, A Doucet, N De Freitas… - Advances in neural …, 2000 - proceedings.neurips.cc
In this paper, we propose a new particle filter based on sequential importance sampling.
The algorithm uses a bank of unscented fil (cid: 173) ters to obtain the importance proposal …

An introduction to sequential Monte Carlo methods

A Doucet, N De Freitas, N Gordon - Sequential Monte Carlo methods in …, 2001 - Springer
Many real-world data analysis tasks involve estimating unknown quantities from some given
observations. In most of these applications, prior knowledge about the phenomenon being …

Competition-level code generation with alphacode

…, E Sutherland Robson, P Kohli, N de Freitas… - Science, 2022 - science.org
Programming is a powerful and ubiquitous problem-solving tool. Systems that can assist
programmers or even generate programs themselves could make programming more …

A generalist agent

…, R Hadsell, O Vinyals, M Bordbar, N de Freitas - arXiv preprint arXiv …, 2022 - arxiv.org
Inspired by progress in large-scale language modeling, we apply a similar approach towards
building a single generalist agent beyond the realm of text outputs. The agent, which we …