At the thirty-second Conference on Neural Information Processing Systems (NeurlPS) in Montreal, Canada, NVIDIA hosted the NVIDIA AI Tech Workshop, a workshop about how GPU-accelerated computing is transforming the landscape of computational science and AI.
“This workshop gives us an opportunity to show the AI community what we’re doing as a company, to help researchers make progress in their work,” said Bryan Catanzaro, NVIDIA’s Vice President of Applied Deep Learning Research.
The sessions explored topics such as mixed precision training, the CUDA ecosystem, NVIDIA hardware, and the latest NVIDIA software development kits.
“What we wanted to do was highlight the software, the products that allow them to achieve their research,” said Kari Briski, Senior Director of Product Management at NVIDIA.
This is the first year the Expo is being held and it comes on the heels of major hardware and software announcements announced at the show.

“A conference like this provides the opportunity to interact and find out what people are working on,” said Stephen Jones, CUDA Systems Engineer at NVIDIA.
This week, NVIDIA announced the NVIDIA TITAN RTX GPU, the world’s most powerful desktop GPU. On the same day, NVIDIA also announced the open source release of PhysX.
Those attending the conference can see the new GPU and meet with NVIDIA researchers and engineers at the NVIDIA booth.
If you missed any of the sessions or were not able to attend the conference — they are available on demand in their entirety on YouTube and after the break.

Workshop Sessions