Presented By O’Reilly and Intel AI
Put AI to Work
April 29-30, 2018: Training
April 30-May 2, 2018: Tutorials & Conference
New York, NY

Accelerate deep neural networks at the edge with the Intel Movidius Neural Compute Stick

9:00am–12:30pm Monday, April 30, 2018
Implementing AI, Models and Methods
Location: Regent Parlor

Who is this presentation for?

  • Developers and company reps at any level

Materials or downloads needed in advance

  • An x86-64 computer running Ubuntu 16.04 (with a USB 2.0 Type A port (recommend USB 3.0), 1 GB RAM, and 4 GB free storage space); a Raspberry Pi 3 Model B running Stretch desktop; or an Ubuntu 16.04 VirtualBox instance
  • Download and install the Intel Movidius Neural Compute SDK

What you'll learn

  • Learn how to use Intel's Movidius Neural Compute Stick

Description

Market research estimates there will be as many as 20 billion connected devices in the market by 2020. These devices are expected to generate billions of petabytes of data traffic between cloud and edge devices. In 2017 alone, there were as many as 8.4B connected devices, highlighting the need to preprocess data at the edge. This has led many IoT device manufacturers, especially those working on vision-based devices like smart cameras, drones, robots, and AR/VR, to bring intelligence to the edge.

Through the recent addition of the Movidius VPU technology to its existing AI edge solutions portfolio, Intel is well positioned to provide solutions to help developers and data scientists pioneer the low-power intelligent edge devices segment. Ashwin Vijayakumar gives you a hands-on overview of Intel’s Movidius Neural Compute Stick, a miniature deep learning hardware development platform that you can use to prototype, tune, and validate your AI programs (specifically deep neural networks).

Topics include:

  • How Movidius VPUs are pioneering DNN-accelerated vision processing
  • The hardware and software components of NCS
  • The workflow of network profiling and application development using NCS
  • Detection and classification models
  • Advanced functionalities
  • A demo and sample code built using NC SDK’s API framework
Photo of Ashwin Vijayakumar

Ashwin Vijayakumar

Intel

Ashwin Vijayakumar is lead developer evangelist and an embedded systems architect working on robotics, IoT, and automotive electronics at Intel. A results-oriented hands-on engineering leader, an entrepreneur, and an innovator with extensive experience in bringing embedded products to market, Ashwin is passionate about deploying products and sustaining them at every stage of product development lifecycle. He is currently focused on the front and rear end of the cycle (i.e., requirements gathering, analysis, prototyping, deployment, training and sales support, and maintenance and technical support).

Comments on this page are now closed.

Comments

Picture of Kathleen Kallot
Kathleen Kallot | PRODUCT MARKETING MANAGER
04/13/2018 2:54pm EDT

There is no need to buy the stick, we will loan the hardware for the tutorial. This is a hands on workshop, so you will be able to experience play with the product

Hao Liu | MANAGER, COMMERICAL DATA SCIENCE
03/22/2018 10:48am EDT

Thanks! Looking forward to it.

Picture of Ashwin Vijayakumar
Ashwin Vijayakumar | LEAD DEVELOPER EVANGELIST
03/19/2018 11:18am EDT

This will be a hands-on workshop/tutorial where the audience will be developing software and deploying it on the Intel Movidius Neural Compute stick. We ask that you bring your own Intel Movidius Neural Compute Stick (NCS) and Ubuntu 16.04 system pre-installed with developer.movidius.com/start. If you do not have either of these, we will bring a few spare systems (laptop & NCS) which you can borrow for the duration of the workshop.

Picture of Jason Perdue
Jason Perdue | SPEAKER MANAGER
03/19/2018 11:10am EDT

The materials and downloads have been updated above.

Hao Liu | MANAGER, COMMERICAL DATA SCIENCE
03/19/2018 10:40am EDT

is this a tutorial, in which attendee can play Movidius together with speaker? or it is just showing how it work by speaker? If we can play with Movidius, do we need to buy and bring Movidius to tutorial? or it is provided?