[Lisa_teatalk] [Lisa_labo] Tea Talk 1 Aug Friday @13.00 AA3195 by Yoshua Bengio

Pierre Luc Carrier carrier.pierreluc at gmail.com
Fri Aug 1 09:37:33 EDT 2014


I cannot make it but I would be very interested in seeing this tea-talk. If
others are in the same situation, perhaps we could look into recording this
tea-talk like we did with guillaume's. I do not know if we have the
material to do this in the lab, though.

Pierre Luc


2014-07-31 17:11 GMT-04:00 Yoshua Bengio <yoshua.bengio at gmail.com>:

> Please ignore the attached pdf, it is a very old version. The arxiv
> version is much better, with many mistakes fixed:
>
>    http://arxiv.org/abs/1407.7906
>
> In the future, of course, the svn version will always be the latest one
> (articles/2014/targetprop).
>
> -- Yoshua
>
>
> On Thu, Jul 31, 2014 at 4:49 PM, Kyung Hyun Cho <cho.k.hyun at gmail.com>
> wrote:
>
>> Dear all,
>>
>> We will have a tea talk this Friday by Prof. Yoshua Bengio. See below for
>> the details and the attached paper.
>>
>> Hope to see many of you there!
>> - Cho
>>
>> ===
>> - Speaker: Prof. Yoshua Bengio (University of Montreal)
>> - Date and Time: 1 Aug 2014 @13.00
>> - Place: AA3195
>> - Title: How Auto-Encoders Could Provide Credit Assignment in Deep
>> Networks via Target Propagation
>> - Abstract:
>> In this paper we propose to exploit reconstruction as a layer-local
>> training signal for deep learning, be it generative or discriminant, single
>> or multi-modal, supervised, semi-supervised or unsupervised, feedforward or
>> recurrent. Reconstructions can be propagated in a form of target
>> propagation playing a role similar to back-propagation but helping to
>> reduce the reliance on back-propagation in order to perform credit
>> assignment across many levels of possibly strong non-linearities (which is
>> difficult for back-propagation). A regularized auto-encoder tends produce a
>> reconstruction that is a more likely version of its input, i.e., a small
>> move in the direction of higher likelihood. By generalizing gradients,
>> target propagation may also allow to train deep networks with discrete
>> hidden units. If the auto-encoder takes both a representation of input and
>> target (or of any side information) in input, then its reconstruction of
>> input representation provides a target towards a representation that is
>> more likely, conditioned on all the side information. A deep auto-encoder
>> decoding path generalizes gradient propagation in a learned way that can
>> thus handle not just infinitesimal changes but larger, discrete changes,
>> hopefully allowing credit assignment through a long chain of non-linear
>> operations. For this to work, each layer must be a good denoising or
>> regularized auto-encoder itself. In addition to each layer being a good
>> auto-encoder, the encoder also learns to please the upper layers by
>> transforming the data into a space where it is easier to model by them,
>> flattening manifolds and disentangling factors. The motivations and
>> theoretical justifications for this approach are laid down in this paper,
>> along with conjectures that will have to be verified either mathematically
>> or experimentally.
>>
>> _______________________________________________
>> Lisa_labo mailing list
>> Lisa_labo at iro.umontreal.ca
>> https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_labo
>>
>>
>
> _______________________________________________
> 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/20140801/5ae7405f/attachment-0001.html 


More information about the Lisa_teatalk mailing list