Beyond the Patterns 28 - Petar Veličković - Geometric Deep Learning

[@Jules-RaymondTapamo]

Great Talk; Truly insightful!

[@hannesstark5024]

Thank you so much for uploading this!

[@49memorylane]

great presentation!- giving us useful ideas for portability. - The core idea of g -->G, being matrices that represent most Deep Learning Models (linear + activation). - But the symmetricity of g doesn't give us a measure of portability across various g's though.. Meaning, the data U they are trying to map are still different probability distributions. (example, a learnt latent vector of human face different from Cars). We are looking into model portability, for better reuse, faster generation. So, maybe look at identifying g's that are closer to each other, with some kind of geometrical tests (thinking out loud)...

[@raghavamorusupalli7557]

Geospatial guys need this model very badly. I applied this concept for image inpainting sometime back.

[@TheAIEpiphany]

Great talk! The group convolutions finally clicked for me after your discussion (48:27 - 57:26)! :)) One comment on my side: 54:20 this dichotomy in Spherical CNNs seems a bit inelegant, every other model you described is uniform in this respect i.e. we just keep on stacking the same types of layers. Any thoughts on this?

[@preyanshrastogi9168]

This lecture is wonderful !!!!

[@chifortudor5105]

Very inspiring presentation.

[@lololololalso]

Thank you !!! I really wonder how GDL will end up with Gestalt principles for computer vision problems.

[@aaryanbhagat4852]

Thanks for this nice upload but it would be more influential if this would be timestamped (same for the future videos).

[@maierAK]

Good Idea! Will do later tonight.

[@maierAK]

Done!

[@manncodes]

Hey, can we have the copy of the slideshow if it's possible?

[@yiquanliu1379]

57:24 Geodesics and Gauges

[@maierAK]

Thanks! I missed that in the description!

[@JethroDjan]

Hello. I am a math person and I get the maths aspect of the talk. But I know next to nothing about deep learning ( or even machine learning for that matter apart from playing around with Tensorflow). Can someone direct me as to where I can start to learn this from a theoretical perspective? I want to do something on this later for thesis... Thanks!

[@maierAK]

You might be interested in this playlist: kzbin.info/www/bejne/iXSphaJ7ZtuAaLc We also have additional coding resources here: lme.tf.fau.de/teaching/free-deep-learning-resources/

[@JethroDjan]

@@maierAK Thanks Prof. Great work!

[@chifortudor5105]

Is there a link to a digital version of the book available ?

[@maierAK]

You can find it here: geometricdeeplearning.com