We can use hangout video conference during the talk.If there are other people who also want to remotely watch the talk, please leave a reply here.Best,--JunyoungOn Mon, Jul 17, 2017 at 2:10 AM, Yoshua Bengio <yoshua.umontreal@gmail.com> wrote:I won't make it but I would really like to watch the presentation and get the slides, if possible.2017-07-17 12:48 GMT+09:00 Junyoung Chung <elecegg@gmail.com>:______________________________Hi all,our next speaker is Eugene Vorontsov. Hope to see you many of you there.When: 13:45, July 21Where: AA6214Title: On orthogonality and learning recurrent networks with long term dependenciesAbstract:
It is well known that it is challenging to train deep neural networks and recurrent neural networks for tasks that exhibit long term dependencies. The vanishing or exploding gradient problem is a well known issue associated with these challenges. One approach to addressing vanishing and exploding gradients is to use either soft or hard constraints on weight matrices so as to encourage or enforce orthogonality. Orthogonal matrices preserve gradient norm during backpropagation and may therefore be a desirable property. This paper explores issues with optimization convergence, speed and gradient stability when encouraging or enforcing orthogonality. To perform this analysis, we propose a weight matrix factorization and parameterization strategy through which we can bound matrix norms and therein control the degree of expansivity induced during backpropagation. We find that hard constraints on orthogonality can negatively affect the speed of convergence and model performance.Bio:
I am a PhD student with professors Chris Pal and Samuel Kadoury at École Polytechnique de Montréal and MILA. I am working on medical image segmentation models and have recently begun developing an interest in optimization and regularization of deep neural networks. Prior to MILA, I studied Engineering Science at the University of Toronto, specializing in biomedical engineering. An aspect of computer science that appealed to me is the fast production of experimental results -- unfortunately, I also like big models.--Junyoung_________________
Lisa_seminaires mailing list
Lisa_seminaires@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_semin aires
_______________________________________________
Lisa_teatalk mailing list
Lisa_teatalk@iro.umontreal.ca
https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_ teatalk