Our Gauge Equivariant CNNs help machines see and understand like humans to improve AI experiences
At Qualcomm AI Research, we’re on a mission to help machines see and understand like humans, and we’re one step closer. Unlike traditional Convolutional Neural Networks (CNN), our Gauge Equivariant CNNs (G-CNNs) can analyze image data on any curved space or geometry, on-device. This means highly efficient AR, VR, autonomous car, and drone experiences. Hear a high-level explanation is this animation video, narrated by Professor Max Welling, Vice President, Technology at Qualcomm Technologies Netherlands B.V.
Read more: https://www.qualcomm.com/news/onq/2019/05/02/helping-machines-see-and-understand-humans
Learn more: https://arxiv.org/abs/1902.04615
Видео Our Gauge Equivariant CNNs help machines see and understand like humans to improve AI experiences канала Qualcomm
Read more: https://www.qualcomm.com/news/onq/2019/05/02/helping-machines-see-and-understand-humans
Learn more: https://arxiv.org/abs/1902.04615
Видео Our Gauge Equivariant CNNs help machines see and understand like humans to improve AI experiences канала Qualcomm
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
![Gauge Equivariant Convolutional Networks and the Icosahedral CNN](https://i.ytimg.com/vi/wZWn7Hm8osA/default.jpg)
![Simulating Natural Selection](https://i.ytimg.com/vi/0ZGbIKd0XrM/default.jpg)
![Gauge Equivariant CNNs, Generative Models, and the Future of AI with Max Welling - TWiML Talk #267](https://i.ytimg.com/vi/CGHOK-O5ZTo/default.jpg)
![Where AI is today and where it's going. | Richard Socher | TEDxSanFrancisco](https://i.ytimg.com/vi/8cmx7V4oIR8/default.jpg)
![Convolutional Neural Networks (CNNs) explained](https://i.ytimg.com/vi/YRhxdVk_sIs/default.jpg)
![Group Equivariant CNNs beyond Roto-Translations: B-Spline CNNs on Lie Groups, Erik Bekkers](https://i.ytimg.com/vi/rakcnrgX4oo/default.jpg)
![Podcast: Everything you need to know about 5G, with Guy Kawasaki and Cristiano Amon](https://i.ytimg.com/vi/XeXHA6z2Ch0/default.jpg)
![Animating 5G: Low Latency](https://i.ytimg.com/vi/SoRzIu1VlC0/default.jpg)
![Learning SO(3) Equivariant Representations with Spherical CNNs](https://i.ytimg.com/vi/Y86rzE4UzKs/default.jpg)
![Animating 5G: Millimeter Wave](https://i.ytimg.com/vi/_HZokKy8Yxk/default.jpg)
![AI Decoded: Distributed Intelligence](https://i.ytimg.com/vi/Y-dVhLnO59M/default.jpg)
![A.I. Learns to play Flappy Bird](https://i.ytimg.com/vi/WSW-5m8lRMs/default.jpg)
![Neural Ordinary Differential Equations - Best Paper Awards NeurIPS 2018](https://i.ytimg.com/vi/V6nGT0Gakyg/default.jpg)
![Capsule Networks: An Improvement to Convolutional Networks](https://i.ytimg.com/vi/VKoLGnq15RM/default.jpg)
![12 Most Mysterious Things Science Still Can't Explain](https://i.ytimg.com/vi/khjdheYDhiw/default.jpg)
![Why China can take a lead in 5G and AI technology application](https://i.ytimg.com/vi/InPzlUE5Qck/default.jpg)
![Demonstrating map projections with Pilot AI on the Qualcomm Vision Intelligence Platform](https://i.ytimg.com/vi/FvWzU6flSLk/default.jpg)
![Demonstrating ConVeX C-V2X with Audi](https://i.ytimg.com/vi/2wb7Ee1H6lo/default.jpg)
![CNN Symmetries (Paper Review Call 022)](https://i.ytimg.com/vi/fLLPgAn2y0w/default.jpg)