Nando de Freitas
homepage:http://www.cs.ox.ac.uk/people/nando.defreitas/
search externally:   Google Scholar,   Springer,   CiteSeer,   Microsoft Academic Search,   Scirus ,   DBlife

Description

Nando de Freitas is Associate professor in the Department of Computer Science at the University of British Columbia .
       The first part of his course will consist of two presentations. In the first presentation, he will introduce fundamentals of Monte Carlo simulation for statistical inference, with emphasis on algorithms such as importance sampling, particle filtering and smoothing for dynamic models, Markov chain Monte Carlo, Gibbs and Metropolis-Hastings, blocking and mixtures of MCMC kernels, Monte Carlo EM, sequential Monte Carlo for static models, auxiliary variable methods (Swedsen-Wang, hybrid Monte Carlo and slice sampling), and adaptive MCMC. The algorithms will be illustrated with several examples: image tracking, robotics, image annotation, probabilistic graphical models, and music analysis.
       The second presentation will target model selection and decision making problems. He will describe the reversible-jump MCMC algorithm and illustrate it with application to simple mixture models and nonlinear regression with an unknown number of basis functions. He will show how to apply this algorithm to general Markov decision processes (MDPs). The course will also cover other Monte Carlo simulation methods for partially observed Markov decision processes (POMDPs) using policy gradients, common random number generation, and active exploration with Gaussian processes. An outline to some applications of these methods to robotics and the design of computer game architectures will be given. The presentation will end with the problem of Monte Carlo simulation for Bayesian nonlinear experimental design, with application to financial modeling, robot exploration, drug treatments, dynamic sensor networks, optimal measurement and active vision.


Lectures:

keynote
flag Learning to learn and compositionality with deep recurrent neural networks
as author at  22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), San Francisco 2016,
459 views
  panel
flag Is Deep Learning the New 42?
as panelist at  22nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), San Francisco 2016,
together with: Andrei Broder (moderator), Pedro Domingos (panelist), Isabelle Guyon (panelist), Jitendra Malik (panelist), Jennifer Neville (panelist),
719 views
lecture
flag New insights on parameter estimation
as author at  NIPS Workshops, Lake Tahoe 2013,
98 views
  lecture
flag Bayesian Optimization in a Billion Dimensions via Random Embeddings
as author at  Large-scale Online Learning and Decision Making (LSOLDM) Workshop, Cumberland Lodge 2013,
343 views
lecture
flag Discussion of Christopher Holmes's talk: What to do about M-open?
as author at  Bayesian Nonparametric Methods: Hope or Hype?,
185 views
  tutorial
flag Sequential Monte-Carlo Methods
as author at  23rd Annual Conference on Neural Information Processing Systems (NIPS), Vancouver 2009,
together with: Arnaud Doucet,
8828 views
tutorial
flag Monte Carlo Simulation for Statistical Inference, Model Selection and Decision Making
as author at  Machine Learning Summer School (MLSS), Kioloa 2008,
28629 views