The ever-increasing number of connected devices requiring real-time responses led to the invention of edge computing, computations are completed on the device rather than centralized servers. Applications requiring edge devices to be deployed at scale or with deep learning programs presents a logistical and maintenance challenge — on top of the resource constraints typically present on edge devices. We’ll discuss the various platforms that can be utilized for deploying intensive deep learning programs, and how you can scale deep learning to the edge in a cost-effective and efficient manner. We’ll undertake a technical deep dive into how NVIDIA’s Jetson platform can be combined as an array solution with multiple modules achieving the performance power of other node server options. Learn from real-world applications where a Jetson-powered inferencing server has achieved cost-effective deep learning at the edge with simplified deployment orchestration.
Speakers:
Patrick Dietrich, CTO, Connect Tech, Inc.
Ryan Collis, CEO, USES Integrated Solutions, Inc.