User profiles for Nando de Freitas
![]() | Nando de FreitasCIFAR & DeepMind Verified email at google.com Cited by 70449 |
Taking the human out of the loop: A review of Bayesian optimization
Big Data applications are typically associated with systems involving large numbers of users,
massive complex software systems, and large-scale heterogeneous computing and …
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 …
Our main result shows that estimating the parameters of an EBM using score matching …
An introduction to MCMC for machine learning
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 …
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 …
cost functions. Bayesian optimization employs the Bayesian technique of setting a prior …
Matching words and pictures
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 …
of segmented images with associated text. Learning the joint distribution of image regions …
[BOOK][B] Sequential Monte Carlo methods in practice
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 …
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 …
The algorithm uses a bank of unscented fil (cid: 173) ters to obtain the importance proposal …
An introduction to sequential Monte Carlo methods
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 …
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 …
programmers or even generate programs themselves could make programming more …
A generalist agent
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 …
building a single generalist agent beyond the realm of text outputs. The agent, which we …