Today we kick off our ICLR 2021 coverage joined by Roberto Bondesan, an AI Researcher at Qualcomm.
Subscribe: iTunes / Google Play / Spotify / RSS
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.
Thanks to our Sponsor!
I’d like to send a huge thank you to our friends at Qualcomm Technologies for their continued support of the podcast, and their sponsorship of this ICLR series! Qualcomm AI Research is dedicated to advancing AI to make its core capabilities — perception, reasoning, and action — ubiquitous across devices. Their work makes it possible for billions of users around the world to have AI-enhanced experiences on devices powered by Qualcomm Technologies. To learn more about what Qualcomm Technologies is up to on the research front, visit twimlai.com/qualcomm.
Connect with Roberto!
- Paper: Probabilistic Numeric Convolutional Neural Networks
- Paper: Spherical CNNs
- Paper: Instance-Adaptive Data Compression
- Paper: Gauge Equivariant Mesh CNNs
- Neural Compression Workshop
- Natural Graph Networks with Taco Cohen
- Neural Augmentation for Wireless Communication with Max Welling
- Gauge Equivariant CNNs, Generative Models, and the Future of AI with Max Welling