Probabilistic Numeric CNNs with Roberto Bondesan - #482

39:31
 
Condividi
 

Manage episode 292158248 series 2355587
Creato da TWIML and Sam Charrington, autore scoperto da Player FM e dalla nostra community - Il copyright è detenuto dall'editore, non da Player FM, e l'audio viene riprodotto direttamente dal suo server. Clicca sul pulsante Iscriviti per rimanere aggiornato su Player FM, o incolla l'URL del feed in un altra app per i podcast.

Today we kick off our ICLR 2021 coverage joined by Roberto Bondesan, an AI Researcher at Qualcomm.

In our conversation with Roberto, we explore his paper Probabilistic Numeric Convolutional Neural Networks, which represents features as Gaussian processes, providing a probabilistic description of discretization error. We discuss some of the other work the team at Qualcomm presented at the conference, including a paper called Adaptive Neural Compression, as well as work on Guage Equvariant Mesh CNNs. Finally, we briefly discuss quantum deep learning, and what excites Roberto and his team about the future of their research in combinatorial optimization.

The complete show notes for this episode can be found at https://twimlai.com/go/482

510 episodi