Presented By O’Reilly and Intel AI
Put AI to work
Sep 4-5, 2018: Training
Sep 5-7, 2018: Tutorials & Conference
San Francisco, CA

In-Person Training
NVIDIA Deep Learning Institute: AI for computer vision and digital content creation

Max Katz (NVIDIA), Eric Levin (NVIDIA)
9:00am-5:00pm
Tuesday, September 4 through Wednesday, September 5
Location: Nob Hill 4/5
Secondary topics:  Computer Vision

Participants should plan to attend training courses on both Tuesday and Wednesday. To attend training courses, you must register for a Platinum or Training pass; does not include access to tutorials on Wednesday.

Max Katz and Eric Levin walk you through the fundamentals of deep learning, from training neural networks to using results to improve performance and capabilities. You'll then apply your newfound knowledge to digital content creation and game development, as you create digital assets with deep learning. No prior deep learning experience is required.

What you'll learn, and how you can apply it

  • Learn how to design, train, and deploy a neural network to create digital assets using deep learning approaches

Prerequisites:

  • No deep learning experience required

Hardware and/or installation requirements:

Max Katz and Eric Levin walk you through the fundamentals of deep learning, from training neural networks to using results to improve performance and capabilities. You’ll then apply your newfound knowledge to digital content creation and game development, as you create digital assets with deep learning.

Outline

Day 1: Fundamentals of deep learning for computer vision

  • Implementing common deep learning workflows, such as image classification and object detection
  • Experimenting with data, training parameters, network structure, and other strategies to increase performance and capability
  • Deploying your neural networks to start solving real-world problems

Day 2: Deep learning for digital content creation using GANs and auto-encoders

  • Training a generative adversarial network (GAN) to generate images
  • Exploring the architectural innovations and training techniques used to make arbitrary video style transfer
  • Training your own denoiser for rendered images

About your instructors

Photo of Max Katz

Max Katz is a solutions architect at NVIDIA, where he supports the US Department of Energy in deploying GPU-accelerated supercomputers and provides assistance to the scientific user community on the use of these systems. His background is in computational astrophysics, a field he still actively does research in. Max holds a PhD in physics from Stony Brook University and a BS and MS in physics from Rensselaer Polytechnic Institute.

Photo of Eric Levin

Eric Levin is a virtual reality developer at NVIDIA, where he works on projects ranging from meditation and anxiety relief for hospitalized pediatric patients and a learn-to-DJ app to social VR dancing and painting experiences. He’s fascinated by the vast potential of the creations that will emerge and evolve as a result of humans and AIs playing and working in partnership together ever more intimately and gracefully.

Conference registration

Get the Platinum pass or the Training pass to add this course to your package.

Comments on this page are now closed.

Comments

Picture of Max Katz
Max Katz | SOLUTIONS ARCHITECT
08/31/2018 6:09am PDT

Hi Shawn, thank you for the feedback. I’m sorry to hear that you’re having that difficulty. I’ve notified our DLI team and they are looking into it. Please e-mail me at mkatz@nvidia.com and I will notify you when we have an update.

Shawn Taylor | R&D MANAGER
08/31/2018 1:53am PDT

Per the course requirements, I have been trying to log in to a DLI account. I follow the emailed link, log on with my existing NVIDIA devzone credentials and get the following error: access_denied: Password login via OIDC-conformant clients with externally-hosted login pages is unsupported. Alternatively, login could have been initiated from the wrong place (e.g., a bookmark).