The recording of my #inaugural talk at @imperialcollege is now available online
This geometric view on deep learning is the convergence of many old and recent research threads and joint work with @joanbruna @PetarV_93 and @TacoCohen
This geometric view on deep learning is the convergence of many old and recent research threads and joint work with @joanbruna @PetarV_93 and @TacoCohen
Joan's 2014 paper on spectral #graphneuralnetworks was my inspiration to get into this field and write our paper with him, @ylecun @trekkinglemon and Arthur Szlam that popularized the term #geometricdeeplearning
Some of the works I mention are due to my amazing students and colleagues @jonathanmasci Davide Boscaini @EmanueleRodola @befcorreia Pablo Gainza @FreyrSverrisson @emaros96 @ffabffrasca @gbouritsas @frederickmonti @b_p_chamberlain @aittalam Kirill Veselkov Guadalupe Gonzalez
Ivan Laponogov @Jozef_Youssef @yuewang314 @JustinMSolomon Ron Kimmel Alex Bronstein Sagi Ben Moshe Dominik Kulon Stefanos Zafeiriou Luca Cosmo @Anees_B_Kazi Nassir Navab @MehdiBahri1 Iasonas Kokkinos (apologies if I forgot someone)
Finally, thanks to @mrahuth for chairing the talk and the questions and to @DanielRueckert for the kind words!
For more details, my blog post in @TDataScience on deriving the convolution from translational symmetry
towardsdatascience.com/deriving-convo…
towardsdatascience.com/deriving-convo…
blog post on latent graph learning, dynamic graph CNNs, and Manifold Learning 2.0
towardsdatascience.com/manifold-learn…
towardsdatascience.com/manifold-learn…
slides are available here: dropbox.com/s/2uyylknoglpu…
• • •
Missing some Tweet in this thread? You can try to
force a refresh
