Go to Tech Hub

Optimize and Scale –Squeeze the Most out of Your Edge AI


SPEAKERS

Director, AI ML Strategy and Technologies
Director of Innovation
Available from October 6

In this session you will learn how multiple edge networks for detection, embeddings and segmentation are combined into a single vision pipeline to solve real-world problems in public safety.

We will examine concurrent and batch processing optimization methods, illustrate when accuracy vs performance trade-offs matter, and we will use NXP’s eIQ software to profile scalability advantages achieved through dynamically refactoring pipelines across a range of edge devices and compute engines.
SEE MORE

RELATED CONTENT


ON-DEMAND TECHNICAL SESSION

Auto-scaling Hardware-agnostic ML Inference with NVIDIA Triton and Arm NN

David Steele

Director of Innovation / Arcturus


Available from October 6 NVIDIA Triton Inference Server simplifies the deployment of AI models at scale in production. With the Arm NN backend, we can orchestrate multi-tenant ML model execution and...

Go to Session

ON-DEMAND TECHNICAL SESSION

Road Trip – Are We There Yet?

David Steele

Director of Innovation / Arcturus


Available from October 6 Reliability and longevity requirements of automotive hardware lifecycle contrast with the need for functional SOTA/FOTA to support growing capabilities and manage complexity...

Go to Session

TECHNICAL SESSIONS WITH Q&A

Low Code Development of a TinyML Predictive Maintenance Solution

David Steele

Director of Innovation / Arcturus


We're going to explain how to quickly develop an anomaly detection solution using the Arduino Portenta hardware and the Arduino software framework. Arduino has championed low-code to enable high pro...

Go to Session