[Seminario] Invitación Grupo de lectura aprendizaje de máquinas Jueves 22 de Septiembre a las 14:00 hrs.
Maria Ines
mrivera en dim.uchile.cl
Mie Sep 21 13:24:12 CLST 2016
Estimados Académicos y alumnos,
Se les invita para este Jueves 22 de Septiembre a las 14:00 hrs, al
Grupo de lectura aprendizaje de máquinas, este se realizará en la Sala
Multimedia del Sexto Piso, Beauchef 851, Torre Norte.
*GLAM #1: The Gaussian Process Convolution Model (Felipe Tobar)
Cuándo: 22/9/16, 1400hrs
Dónde: Sala multimedia, 6to piso, CMM
*
Tobar, Bui and Turner, "Learning Stationary Time Series using Gaussian
Processes with Nonparametric Kernels", Neural information processing
systems, 2015.
*Abstract: *We introduce the Gaussian Process Convolution Model (GPCM),
a two-stage nonparametric generative procedure to model stationary
signals as the convolution between a continuous-time white-noise process
and a continuous-time linear filter drawn from Gaussian process. The
GPCM is a continuous-time nonparametric-window moving average process
and, conditionally, is itself a Gaussian process with a nonparametric
kernel defined in a probabilistic fashion. The generative model can be
equivalently considered in the frequency domain, where the power
spectral density of the signal is specified using a Gaussian process.
One of the main contributions of the paper is to develop a novel
variational free-energy approach based on inter-domain inducing
variables that efficiently learns the continuous-time linear filter and
infers the driving white-noise process. In turn, this scheme provides
closed-form probabilistic estimates of the covariance kernel and the
noise-free signal both in denoising and prediction scenarios.
Additionally, the variational inference procedure provides closed-form
expressions for the approximate posterior of the spectral density given
the observed data, leading to new Bayesian nonparametric approaches to
spectrum estimation. The proposed GPCM is validated using synthetic and
real-world signals.
------Próximas sesiones (tentativa):
1) The Gaussian Process Convolution Model (Felipe Tobar, 22/9)
3) Sparse and online Gaussian Processes (Christopher Ley, 29/9)
2) Warped Gaussian Processes (Gonzalo Ríos, 6/10)
4) Multi-output Gaussian processes (Gabriel Parra, 13/10)
5) Identificación de sistemas usando kernels (Alejandro Bernardín, 20/10)
6) Inferencia de Monte Carlo (Donato Vásquez, 27/10)
7) Inferencia Variacional (F. Tobar + I. Castro, 3/11)
8) Procesos de Dirichlet (Joaquín Rojas, 17/11)
9) Deep Neural Networks (Matías Silva, 24/11)
10) Random Forests (Romain Gouron, 1/12)
11) Probabilistic Graphical models (Ignacio Reyes, 8/12)
Esperando contar con su presencia, les saluda,
Ma. Inés Rivera
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://listas.dim.uchile.cl/pipermail/seminario/attachments/20160921/31e70f5e/attachment.html>
Más información sobre la lista de distribución Seminario