[Lisa_seminaires] [Lisa_montreal] [TeaTalk] Iulian Serban (Wednesday, Aug 30) and Andrew Jesson (Friday, Sept 1)

Iulian Serban julianserban at gmail.com
Mer 30 Aou 14:12:37 EDT 2017


We got the key and moved the talked to Z-209. We have 30+ people here,
please come here.

- Julian

On 30 August 2017 at 14:04, Dzmitry Bahdanau <dimabgv at gmail.com> wrote:

> Because we don't have the keys *the talk is moved to AA3195*.
>
> Dima
>
> On Wed, 30 Aug 2017 at 13:51 Dzmitry Bahdanau <dimabgv at gmail.com> wrote:
>
>> The talk will start with *a short delay of ~10 minutes, at 14:10 *(the
>> speaker is stuck in traffic).
>>
>> Dima
>>
>>
>> On Wed, 30 Aug 2017 at 10:10 Dzmitry Bahdanau <dimabgv at gmail.com> wrote:
>>
>>> A kind reminder: Iulian's talk is today! And it's also a LURG meeting,
>>> 2-in-1.
>>>
>>> On Mon, 28 Aug 2017 at 08:40 Dzmitry Bahdanau <dimabgv at gmail.com> wrote:
>>>
>>>> Hi all,
>>>>
>>>> We are lucky to have two speakers this week!
>>>>
>>>> First,* Iulian Serban* will tell us about the progress of MILA team in
>>>> Alexa challenge (*Z-209 between 14h00 - 15h00, August 30th*).
>>>>
>>>> Next, we will learn about deep learning with extreme class imbalance
>>>> from *Andrew Jesson *from Imagia (*AA6214, 13:45  - 14:45, September 1*
>>>> ).
>>>>
>>>> Please find the details below.
>>>>
>>>> Dima
>>>>
>>>> *Speaker:* Iulian Serban
>>>>
>>>> *Title:* A Deep Reinforcement Learning Chatbot
>>>>
>>>> *Abstract*: We present MILABOT: a deep reinforcement learning chatbot
>>>> developed at MILA for the Amazon Alexa Prize competition. MILABOT is
>>>> capable of conversing with humans on popular small talk topics through both
>>>> speech and text. The system consists of an ensemble of natural language
>>>> generation and retrieval models, including sequence-to-sequence and latent
>>>> variable neural network models. By applying reinforcement learning to
>>>> crowd-sourced data and real-world user interactions, the system has been
>>>> trained to select an appropriate response from the models in its ensemble.
>>>> The system has been evaluated through A/B testing with real-world users,
>>>> where it performed excellent compared to competing systems.
>>>>
>>>> *Bio:* Iulian Serban is a PhD candidate at MILA, where he investigates
>>>> deep learning and reinforcement learning methods for dialogue and other
>>>> natural language processing applications. Iulian is supervised by Yoshua
>>>> Bengio, Aaron Courville and Joelle Pineau. He holds an MSc in machine
>>>> learning from University College London, and a BSc in theoretical
>>>> mathematics and statistics from Copenhagen University. Previously, Iulian
>>>> worked at DigiCorpus ApS, where he developed a physiotherapy computer
>>>> vision system, now deployed in clinics across Denmark.
>>>>
>>>> *Speaker:* Andrew Jesson
>>>>
>>>> *Title:* CASED: Curriculum Adaptive Sampling for Extreme Data Imbalance
>>>>
>>>> *Abstract: *We introduce CASED, a novel curriculum sampling algorithm
>>>> that facilitates the optimization of deep learning segmentation or
>>>> detection models on data sets with extreme class imbalance. We evaluate the
>>>> CASED learning framework on the task of lung nodule detection in chest CT.
>>>> In contrast to two-stage solutions wherein nodule candidates are first
>>>> proposed by a segmentation model and then refined by a second detection
>>>> stage, CASED improves the training of deep nodule segmentation models (e.g.
>>>> UNet) to the point where state of the art results are achieved using only a
>>>> trivial detection stage. CASED improves the optimization of deep
>>>> segmentation models by allowing them to first learn how to distinguish
>>>> nodules from their immediate surroundings, while continuously adding a
>>>> greater proportion of difficult-to-classify global context, until uniformly
>>>> sampling from the empirical data distribution. Using CASED during training
>>>> yields a minimalist proposal to the lung nodule detection problem
>>>> competitive the LUNA16 nodule detection benchmark with an average
>>>> sensitivity score of 88.7%. Furthermore, we find that models trained using
>>>> CASED are robust to nodule annotation quality by showing that comparable
>>>> results can be achieved when only a point and radius for each ground truth
>>>> nodule are provided during training. Finally, the CASED learning framework
>>>> makes no assumptions with regard to imaging modality or segmentation target
>>>> and so should generalize to other medical imaging problems where class
>>>> imbalance is a persistent problem.
>>>>
>>>> *Bio:* Andrew Jesson is the leader of the new A.I. Research team at
>>>> Imagia. He is currently subitting his Master's thesis in electrical
>>>> engineering with a focus on medical imaging at McGill University. Andrew
>>>> has spent the last 12 years in Montreal where he has aslo earned a B.A. in
>>>> philosophy from Concordia University and a B.Eng from McGill.
>>>>
>>>>
>>>>
> _______________________________________________
> Lisa_montreal mailing list
> Lisa_montreal at iro.umontreal.ca
> https://webmail.iro.umontreal.ca/mailman/listinfo/lisa_montreal
>
>
-------------- section suivante --------------
Une pièce jointe HTML a été nettoyée...
URL: http://webmail.iro.umontreal.ca/pipermail/lisa_seminaires/attachments/20170830/d50fc041/attachment-0001.html 


Plus d'informations sur la liste de diffusion Lisa_seminaires