NTR Webinar: Hyperbolic Image Embeddings

NTR organizes and hosts scientific webinars on neural networks and invites speakers from all over the world to present their recent work at the webinars.

On July 27 Leyla Mirvakhabova, Skolkovo Institute of Science and Technology (Skoltech), Moscow, Russia, led a technical Zoom webinar on Hyperbolic Image Embeddings. 

About the webinar: 

In this talk, I discussed our paper ‘Hyperbolic Image Embeddings’. 

Usually, computer vision methods use either Euclidean or spherical distances; in this work, we proposed to use hyperbolic geometry. 

I started with an overview of different machine learning methods based on hyperbolic geometry; then, I talked briefly about few-shot learning and, finally, described our experimental setup.

Webinar presentation.

Moderator and contact: NTR CEO Nick Mikhailovsky: nickm@ntrlab.com.

Leave a Reply

Your email address will not be published. Required fields are marked *