December 7th Webinar: Integrating AI/ML at the Edge with the SOSA™ Technical Standard
This webinar will be held on December 7, 2021
11:00 AM EST / 10:00 AM CST / 8:00 AM PST / 4:00 PM GMT
AI continues to have its impact on military computing projects, and applications involving the new architecture SOSA is no exception.
This webcast will examine how the newly released Sensor Open Systems Architecture™ (SOSA) leverages AI technologies to implement the use of video and data analytics at the edge with building blocks aligned to the open standard.
Key building blocks will be introduced through the use of a mock proposal and sample payload. Through this exercise, the speakers will demonstrate:
- How to build a system
- Which elements to include
- How to scale the technologies
- Ease of system configuration using SOSA
- The benefits of interoperability
Technical details covered will include:
- How to select a backplane to build the overarching reference architecture
- NVIDIA’s Ampere architecture, which provides dedicated cores for AI optimization and addresses low latency requirements critical to military applications
- The latest single board computers using Intel’s Tiger Lake chipset supporting PCIe Gen 4, and how the “heart” of the system interconnects the components
- Addressing security questions with separate data and control planes
- How data gets passed and process within the system’s GPGPU
The presentations will be followed by a Q&A session, so bring your questions to what promises to be a very informative event.
Presented by:
Mark Littlefield is senior manager of embedded computing products and services for Elma Electronic. He is an active contributor to multiple VITA and SOSA technical working groups, leads the SOSA small form factor (SFF) sub-committee, and was co-chair of the VITA 65 OpenVPX working group. He has more than 25 years of experience in embedded computing, where he has held a range of technical and professional roles supporting defense, medical, and commercial applications. Mark holds bachelor's and master’s degrees in control systems engineering from the University of West Florida, where he wrote his thesis on a neural net approach to image processing.
Nigel Forrester Director of Business Development Concurrent Technologies
Nigel Forrester has responsibility for product strategy and partner relationships along with a focus on outbound marketing activities. He has previous experience of technical product and vertical marketing roles in the embedded space and is an accomplished speaker and author. Nigel is based at Concurrent Technologies UK headquarters.
Chris Fadeley is a Software Engineering Manager at EIZO Rugged Solutions (ERS) with a strong background in embedded software engineering. He leads all of ERS initiatives in AI, Deep Learning, GPGPU processing and optimization. Chris and his team develop unified drivers and APIs that integrate with all of NVIDIA’s software stack and allow interoperability of company’s rugged graphics and video products in most system configurations. He holds a BS Computer Engineering Degree from the University of Florida.
John KellerEditor-in-Chief Military & Aerospace Electronics
This event is sponsored by: