[Tea Talk] Devon Hjelm (MSR Montreal + Mila) Fri October 12 2018 10:30 JC S1-111
This week we have our very own *Devon Hjelm * from * MSR Montreal x Mila * giving a talk on *Friday October 12 2018* at *10:30* in room *Jean Coutu S1-111* Will this talk be streamed <https://mila.bluejeans.com/809027115/webrtc>? No Will this talk be recorded? Yes Maximize your own information and come learn at this talk! Michael *TITLE* Learning representations with Deep InfoMax *KEYWORDS *representation learning, unsupervised learning, adversarial learning *ABSTRACT* In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about locality of the input to the objective can greatly influence a representation’s suitability for downstream tasks. We further control characteristics of the representation by matching to a prior distribution adversarially. Our method, which we call Deep InfoMax (DIM), outperforms a number of popular unsupervised learning methods and competes with fully-supervised learning on several classification tasks. DIM opens new avenues for unsupervised learning of representations and is an important step towards flexible formulations of representation-learning objectives for specific end-goals (https://arxiv.org/abs/1808.06670) *BIO* Devon Hjelm is a researcher at Microsoft Research Montreal and an Adjunct Professor at MILA. He did his postdoc at MILA where he focused on adversarial learning and generative models. His current research focuses on using mutual information estimation objectives in representation learning for applications in computer vision, natural language, and RL.
Reminder: talk in 30 minutes! Note the different room (in Jean Coutu) On Tue, Oct 9, 2018, 17:12 Michael Noukhovitch <mnoukhov@gmail.com> wrote:
This week we have our very own *Devon Hjelm * from * MSR Montreal x Mila * giving a talk on *Friday October 12 2018* at *10:30* in room *Jean Coutu S1-111*
Will this talk be streamed <https://mila.bluejeans.com/809027115/webrtc>? No Will this talk be recorded? Yes
Maximize your own information and come learn at this talk! Michael
*TITLE* Learning representations with Deep InfoMax
*KEYWORDS *representation learning, unsupervised learning, adversarial learning
*ABSTRACT* In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about locality of the input to the objective can greatly influence a representation’s suitability for downstream tasks. We further control characteristics of the representation by matching to a prior distribution adversarially. Our method, which we call Deep InfoMax (DIM), outperforms a number of popular unsupervised learning methods and competes with fully-supervised learning on several classification tasks. DIM opens new avenues for unsupervised learning of representations and is an important step towards flexible formulations of representation-learning objectives for specific end-goals (https://arxiv.org/abs/1808.06670)
*BIO* Devon Hjelm is a researcher at Microsoft Research Montreal and an Adjunct Professor at MILA. He did his postdoc at MILA where he focused on adversarial learning and generative models. His current research focuses on using mutual information estimation objectives in representation learning for applications in computer vision, natural language, and RL.
Sorry for the late notice. Talk is moved to 3195. Le ven. 12 oct. 2018 09:59, Michael Noukhovitch <mnoukhov@gmail.com> a écrit :
Reminder: talk in 30 minutes! Note the different room (in Jean Coutu)
On Tue, Oct 9, 2018, 17:12 Michael Noukhovitch <mnoukhov@gmail.com> wrote:
This week we have our very own *Devon Hjelm * from * MSR Montreal x Mila * giving a talk on *Friday October 12 2018* at *10:30* in room *Jean Coutu S1-111*
Will this talk be streamed <https://mila.bluejeans.com/809027115/webrtc>? No Will this talk be recorded? Yes
Maximize your own information and come learn at this talk! Michael
*TITLE* Learning representations with Deep InfoMax
*KEYWORDS *representation learning, unsupervised learning, adversarial learning
*ABSTRACT* In this work, we perform unsupervised learning of representations by maximizing mutual information between an input and the output of a deep neural network encoder. Importantly, we show that structure matters: incorporating knowledge about locality of the input to the objective can greatly influence a representation’s suitability for downstream tasks. We further control characteristics of the representation by matching to a prior distribution adversarially. Our method, which we call Deep InfoMax (DIM), outperforms a number of popular unsupervised learning methods and competes with fully-supervised learning on several classification tasks. DIM opens new avenues for unsupervised learning of representations and is an important step towards flexible formulations of representation-learning objectives for specific end-goals (https://arxiv.org/abs/1808.06670)
*BIO* Devon Hjelm is a researcher at Microsoft Research Montreal and an Adjunct Professor at MILA. He did his postdoc at MILA where he focused on adversarial learning and generative models. His current research focuses on using mutual information estimation objectives in representation learning for applications in computer vision, natural language, and RL.
-- 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@mila.quebec.
participants (2)
-
Michael Noukhovitch -
xavier bouthillier