[Lisa_teatalk] [Lisa_labo] (sans objet)

Li Yao yaoli.email at gmail.com
Thu Nov 12 13:49:28 EST 2015


Is there a write-up about this topic, for some of us who cannot be there?

On Thu, Nov 12, 2015 at 11:44 AM, Jörg Bornschein <bornj at iro.umontreal.ca>
wrote:

> Hi,
>
>
> I would like to announce my own tea-talk for tomorrow -- starting at
> 2:30pm in AA3195. I will present some joint work with Asja and Samira:
>
>
>
> Time: 2:30pm - 3:30pm
>
> Where: AA3195
>
> Title: Training deep generative (bidirectional) Helmholtz-Machines
>
> == Abstract ==
>
>
> Unsupervised training of deep generative models containing latent
> variables and performing inference remains a challenging problem. Various
> methods have been proposed and many of them train an auxiliary model to
> perform approximate inference for the generative model which is fitted to
> the training data. The top-down generative model is typically a directed
> model that starts from some prior over latent variables at the top, down to
> a distribution over the observed variables at the bottom. The approximate
> inference model runs in the opposite direction and is typically trained to
> efficiently infer high probability latent states given some observed data.
> After presenting some of the well-known / state-of-the-art approaches
> (Wake sleep, NVIL and VAE) I will to talk about a new method we have been
> investigating, called a bidirectional Helmholtz machine (BiHM), that is
> based on the idea that the generative model should be close to the class of
> distributions that can be modeled by our approximate inference
> distribution. We achieve this by interpreting both the top-down and the
> bottom-up directed models as approximate inference distributions and by
> defining the target distribution we fit to the training data to be the
> geometric mean of these two. We present an upper-bound for the
> log-likelihood of this model and we show that optimizing this bound will
> pressure the model to stay close to the approximate inference distributions.
>
>
>
> Hope to see you tomorrow!
>
>
> j
>
>
> _______________________________________________
> Lisa_labo mailing list
> Lisa_labo at iro.umontreal.ca
> https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_teatalk/attachments/20151112/909c47f9/attachment.html 


More information about the Lisa_teatalk mailing list