[Lisa_seminaires] Fwd: Announce of the Thesis Defense of CHUNG, Junyoung - Ph.D. at University of Montreal

Yoshua Bengio yoshua.umontreal at gmail.com
Ven 9 Mar 08:03:37 EST 2018


Hi all,

Junyoung Chung will defend his PhD thesis on March 20th (Tuesday) at 9am at
PAA Z-209. Please come and honour his success.

Here is the title and abstract of the thesis:

On Deep Multiscale Recurrent Neural Networks

In this thesis, a subgroup of deep learning models, known as recurrent
neural networks is studied in depth. Recurrent neural networks are special
types of artificial neural networks that possess more strength in
modeling temporal
structures of sequential data such as text and speech. Recurrent neural
networks are used as the core module of many practical applications
including speech recognition, text-to-speech, machine translation, machine
comprehension, and question and answering. This thesis includes a series of
studies towards deep multiscale recurrent neural networks and novel
architectures to overcome the inherent problems of recurrent neural
networks.


There are three articles that propose advanced network architectures to
implement deep multiscale recurrent neural networks. In the first article,
we introduce a new type of network architecture that adds more
communication channels to the recurrent neural networks. The recurrence is
not only restricted to self-connections as the conventional recurrent
neural networks do but fully connected between all hidden layers at
consecutive time steps. the influence of information passing through the
channel is adaptively controlled by parameterized gating units. In the
second article, we study a neural machine translation system that exploits
a character-level decoder. The motivation behind this work is to answer a
fundamental question of generating a sequence of characters as translation
instead of a sequence of words. We design a two-layered recurrent neural
network architecture that captures fast and slow components of a sequence
in a separate manner. In the third article, we investigate a recurrent
neural network architecture that can change the states of hidden layers in
multiple timescales in order to capture the hierarchical temporal structure
of sequences. The proposed framework introduces a set of boundary detecting
units that are used to find terminations of meaningful chunks. The
inclusion of the boundary detectors leads to a novel update mechanism that
allows the recurrent neural networks to update each hidden layer with a
different timescale based on the states of the boundary detectors.


Finally, in the fourth article, we study the inclusion of latent variables
to recurrent neural networks. The complexity and high signal-to-noise ratio
of sequential data such as speech make it difficult to learn meaningful
structures from the data. We propose a recurrent extension of the
variational auto-encoder in order to introduce high-level latent variables
to recurrent neural networks and show significant performance improvement
on sequence modeling tasks such as human speech signals and handwriting
examples.


---------- Message transféré ----------
De : Celine Begin <beginc at iro.umontreal.ca>
Date : 8 mars 2018 à 07:51
Objet : Announce of the Thesis Defense of CHUNG, Junyoung - Ph.D. at
University of Montreal
À : Miklos Csuros <miklos.csuros at umontreal.ca>, Yoshua Bengio <
bengioy at iro.umontreal.ca>, Alain Tapp <tappa at iro.umontreal.ca>,
hochreit at bioinf.jku.at, Junyoung Chung <elecegg at gmail.com>


Good morning,

You are cordially invited to the Thesis Defense of Junyoung Chung
which will take place on Tuesday, March 20th at 9:00 am
in room Z-209 of Claire-McNicholl building.

You will find attached the announcement of this Thesis Defense.

Presently, I did receive a confirmation about "le représentant du doyen de
la FAS".
Maybe next week.

Thanks,
Best,

-- 

S.v.p. Mentionner votre nom et numéro de matricule dans votre courriel
--
   Céline Bégin
   Technicienne à la gestion des dossiers étudiants
   Programmes Maitrise informatique,
     Maitrise en Commerce électronique et
     Doctorat en informatique
   Université de Montréal
   Département d'informatique et de recherche opérationnelle
   Pavillon André Aisenstadt, 2920 chemin de la tour, bureau 2151
   Montréal (Québec) H3T 1J4
   téléphone  : 514-343-6111 <(514)%20343-6111> poste 3492
   télécopieur: 514-343-5834 <(514)%20343-5834>
   courriel   : agde3 at iro.umontreal.ca
-------------- section suivante --------------
Une pièce jointe HTML a été nettoyée...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_seminaires/attachments/20180309/7947752d/attachment-0001.html 
-------------- section suivante --------------
Une pièce jointe non texte a été nettoyée...
Nom: Soutenance_Annonce_Modele.pdf
Type: application/pdf
Taille: 18339 octets
Desc: non disponible
Url: http://webmail.iro.umontreal.ca/pipermail/lisa_seminaires/attachments/20180309/7947752d/attachment-0001.pdf 


Plus d'informations sur la liste de diffusion Lisa_seminaires