[Lisa_seminaires] [teatalk-orgs] Re: Anirudh Goyal, September 15, AA6214, 11AM

Michael Noukhovitch mnoukhov at gmail.com
Ven 15 Sep 10:45:47 EDT 2017


This talk is in 15 minutes! See you all there!

Michael

On Fri, Sep 15, 2017, 09:40 Dzmitry Bahdanau <dimabgv at gmail.com> wrote:

> Hi all,
>
> Just a kind reminder that this talk will take place today!
>
> Dima
>
> On Wed, 13 Sep 2017 at 17:20 Michael Noukhovitch <mnoukhov at gmail.com>
> wrote:
>
>> Hi All!
>>
>> Dima is going on an internship so I'll be organizing tea talks for the
>> next couple of months!
>>
>> This week, our very own *Anirudh* will present his NIPS paper (congrats
>> btw!) it will be at *AA6214 on Friday September 15th, 11AM *Hope to see
>> everyone there!
>>
>> *Title:* Z-Forcing: Training Stochastic Recurrent Networks
>>
>> *Abstract:* Many efforts have been devoted to training generative latent
>> variable models with autoregressive decoders, such as recurrent neural
>> networks (RNN). Stochastic recurrent models have been successful in
>> capturing the variability observed in natural sequential data such as
>> speech. We propose a novel sequential latent variable model unifying
>> successful ideas from recently proposed architectures: each step in the
>> sequence is associated with a latent variable that is used to condition the
>> recurrent dynamics for future steps. Training is performed with amortised
>> variational inference where the approximate posterior is augmented with a
>> RNN that runs backward through the sequence. In addition to maximizing the
>> variational lower bound, we ease training of the latent variables by adding
>> an auxiliary cost which forces them to reconstruct the state of the
>> backward recurrent network. This provides the latent variables with a
>> task-independent objective that enhances the performance of the overall
>> model. Although being conceptually simple, our model achieves
>> state-of-the-art results on standard speech benchmarks such as TIMIT and
>> BLIZZARD and competitive performance on sequential MNIST. Finally, we apply
>> our model on language modeling in the IMDB dataset. The auxiliary cost is
>> crucial for learning interpretable latent variables.
>>
>> Michael
>>
>> --
>> You received this message because you are subscribed to the Google Groups
>> "Tea Talks MILA" group.
>> To unsubscribe from this group and stop receiving emails from it, send an
>> email to teatalk-orgs+unsubscribe at lisa.iro.umontreal.ca.
>> To post to this group, send email to teatalk-orgs at lisa.iro.umontreal.ca.
>> To view this discussion on the web visit
>> https://groups.google.com/a/lisa.iro.umontreal.ca/d/msgid/teatalk-orgs/CAMVr0Vz9qZWu%3Dwa4kqaDO6qukMzn9m0PSEHA%2BUPUwEa6Y5FapA%40mail.gmail.com
>> <https://groups.google.com/a/lisa.iro.umontreal.ca/d/msgid/teatalk-orgs/CAMVr0Vz9qZWu%3Dwa4kqaDO6qukMzn9m0PSEHA%2BUPUwEa6Y5FapA%40mail.gmail.com?utm_medium=email&utm_source=footer>
>> .
>>
> --
> You received this message because you are subscribed to the Google Groups
> "Tea Talks MILA" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to teatalk-orgs+unsubscribe at lisa.iro.umontreal.ca.
> To post to this group, send email to teatalk-orgs at lisa.iro.umontreal.ca.
> To view this discussion on the web visit
> https://groups.google.com/a/lisa.iro.umontreal.ca/d/msgid/teatalk-orgs/CAL_QA9keOmrCoH7wLe%2BhNVDPds%3D-CCTf8NW-LMfeYqWWa%2BMP%3Dg%40mail.gmail.com
> <https://groups.google.com/a/lisa.iro.umontreal.ca/d/msgid/teatalk-orgs/CAL_QA9keOmrCoH7wLe%2BhNVDPds%3D-CCTf8NW-LMfeYqWWa%2BMP%3Dg%40mail.gmail.com?utm_medium=email&utm_source=footer>
> .
>
-------------- section suivante --------------
Une pièce jointe HTML a été nettoyée...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_seminaires/attachments/20170915/985445df/attachment.html 


Plus d'informations sur la liste de diffusion Lisa_seminaires