Confirmed Tutorial Lecturer
Dr. Sofiane Yous
Engineering Lead / Lead Architect
Embedded Machine Intelligence at Intel Corporation
Accelerate Deep Learning Inference at the edge with Intel® Movidius™ VPU Technology
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 Intel® Movidius™ Vision Processing Unit (Intel® 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. Dr. Sofiane Yous will introduce the key features of Intel Movidius VPU technology and give you a hands-on overview of the Intel® 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).
- Introduction to edge analytics and embedded DNN inference
- The challenges associated with efficient design of embedded DNN applications
- Intel Movidius VPUs as a leading solution for DNN-accelerated vision processing platforms
- Overview of hardware and software components of NCS
- The workflow of network profiling and application development using NCS
- Advanced functionalities
- Deployment of detection and classification models
- A demo and sample code built using Intel® Movidius™ Neural Compute SDK’s API framework