[Lisa_seminaires] [mila-tous] Re: [Tea Talk] Anirudh Goyal (Mila) Fri 5 April 2019 10h30 Mila Auditorium

Pablo Fonseca palefo at gmail.com
Ven 5 Avr 10:55:51 EDT 2019


The streaming link is  https://mila.bluejeans.com/4862024040/webrtc
<https://www.google.com/url?q=https%3A%2F%2Fmila.bluejeans.com%2F4862024040%2Fwebrtc&sa=D&usd=2&usg=AFQjCNGqbTWFulqOxxIoTuNpaxpDzb3XCw>

On Fri, Apr 5, 2019 at 9:59 AM Rim Assouel <rim.assouel at gmail.com> wrote:

> Reminder that this happens in 30 minutes :)
>
> Le lundi 1 avril 2019, Rim Assouel <rim.assouel at gmail.com> a écrit :
>
>> This week we have * Anirudh Goyal* from * Mila * giving a talk on *
>> Inductive Biases, Invariances and Generalization* at * 10h30* in room *
>> Mila Auditorium*.
>>
>> Will this talk be streamed <https://mila.bluejeans.com/809027115/webrtc>?
>> yes
>>
>> See you there!
>> The Tea Talk Team
>>
>> *TITLE* Inductive Biases, Invariances and Generalization
>>
>> *ABSTRACT*
>> The biggest challenge right now in RL specifically, AI more generally, is
>> to devise methods for learning complex behaviours that have meaningful
>> generalization. In supervised learning (vision, speech, NLP), it seems that
>> deep models can achieve very complex generalization, but this is not really
>> the case in RL. In this talk, I'm going to first argue that this gap in
>> generalization has much to do with current practices in evaluating
>> generalization in multitask, transfer and meta-learning setups, and then
>> I'm going to talk about an elegant solution for learning complex inductive
>> biases that can be used to exploit the structure of the task, thus enabling
>> the learning agent to incorporate prior knowledge into the learning system
>> to exploit reusable structure in task space.
>>
>> *BIO*
>> Anirudh Goyal is a first year PhD student advised by Prof. Yoshua Bengio.
>> His current research interests center around understanding the interplay
>> b/w three words: Invariances, Inductive Biases and Generalization.
>>
> --
> You received this message because you are subscribed to the Google Groups
> "MILA Tous" group.
> To unsubscribe from this group and stop receiving emails from it, send an
> email to mila-tous+unsubscribe at mila.quebec.
>
-------------- section suivante --------------
Une pièce jointe HTML a été nettoyée...
URL: <http://mailman.iro.umontreal.ca/pipermail/lisa_seminaires/attachments/20190405/1ed40ca9/attachment.html>


Plus d'informations sur la liste de diffusion Lisa_seminaires