[Lisa_teatalk] Tea Talk 11 June Tomorrow @13:00 AA3195 by Prof. Tapani Raiko

Kyung Hyun Cho cho.k.hyun at gmail.com
Tue Jun 10 12:07:41 EDT 2014


Dear all,

Prof. Tapani Raiko will introduce his recent work on extending NADE into
NADE-k tomorrow at the tea talk (http://arxiv.org/abs/1406.1485, the paper
attached).

=======

- Speaker: Prof. Tapani Raiko (Aalto University, Finland)
- Date and Time: 11 June 2014 @ 13.00
- Place: AA3195
- Abstract:
Training of the neural autoregressive density estimator (NADE) can be
viewed as doing one step of probabilistic inference on missing values in
data. We propose a new model that extends this inference scheme to multiple
steps, arguing that it is easier to learn to improve a reconstruction in k
steps rather than to learn to reconstruct in a single inference step. The
proposed model is an unsupervised building block for deep learning that
combines the desirable properties of NADE and multi-predictive training:
(1) Its test likelihood can be computed analytically, (2) it is easy to
generate independent samples from it, and (3) it uses an inference engine
that is a superset of variational inference for Boltzmann machines. The
proposed NADE-k has state-of-the-art performance in density estimation on
the two datasets tested.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_teatalk/attachments/20140610/93775f8e/attachment-0001.html 
-------------- next part --------------
A non-text attachment was scrubbed...
Name: 1406.1485v1(1).pdf
Type: application/pdf
Size: 689512 bytes
Desc: not available
Url : http://webmail.iro.umontreal.ca/pipermail/lisa_teatalk/attachments/20140610/93775f8e/attachment-0001.pdf 


More information about the Lisa_teatalk mailing list