How can you accelerate software at the Edge? We are all familiar with being able to accelerate model learning and training through the use of GPU Acceleration, built-in processors and embedded software. With limited CPU, memory and storage at the edge, these traditional approaches to acceleration can be a challenge. And it’s not only at the ‘model and application level’ where software can be accelerated. We can also accelerate software by improving our infrastructure management and deployment methods (e.g. OS image generation and management). Some scientists have turned to pruning and quantizing their larger models which can make the models smaller and easier to deploy to the Edge. Although pruning and quantization can produce more performant models, the models themselves can be less accurate. And model accuracy is something that many companies can not sacrifice. What options are left? In this session, we will look at current model training and execution at the edge and examine interesting acceleration alternatives in the areas of data augmentation and data curration strategies, containerized models and applications.

Audrey Reznik Guidera,

Senior Principal Software Engineer, Red Hat

Whether or not Henry Ford really said: “If I had asked people what they wanted, they would have said faster horses.”, the quote encapsulates the spirit of true innovation, and the idea of leap-frogging changes. So if you are striving to improve and optimize business processes, you might find yourself dealing with new technologies like Drones, Edge Computing, 5G, AI, DevOps or GitOps. This workshop is based on a precision agriculture scenario and demo featuring drones, 5G slices, Edge computing, Computer vision, and Operations Research. All of it orchestrated and developed on OpenShift and OpenShift Data Science. In this zero-to-hero workshop, we will learn how to mix all those ingredients and will go in-depth in the different aspects of an innovative end-to-end architecture that can also be applied to other fields like Smart Cities, Industrial IoT, Telehealth and many more.

Guillaume Moutier,

Senior Principal Data Engineering Architect, Red Hat

Real time detection, alerting and remediation of product, equipment and behavioural anomalies can be challenging in cross-industry edge scenarios: Manufactacturing plants (faulty equipment and product imperfections); Retail outlets (faulty product, foot traffic, shoplifting); Transportation hubs and vehicles (equipment maintenance, goods and packaging); Mining sites, oilfields and wind farms (faulty or unsafe equipment degradation). In concert with Red Hat partner Guise.ai we will demonstrate an AI based edge solution that addresses these challenges such as eliminating false-positives amongst a myriad of permutations of allowed and OK scenarios. We will showcase an end-to-end solution that does: Real-time anomaly detection at the edge; AI model training; Model Optimization; MLOPs. Our architecture is: Scalable to cover deployment to multiple edge locations; Extensible to cater for many different edge use cases. The solution will show how Red Hat enables customers and partners to win with a consistent approach across core, edge and cloud.

Have you ever wandered into a department store and wondered if the item you are looking at is on sale? What if you had the ability to scan the item ‘yourself’ and determine if it was discounted? That ‘ability’ would make your shopping experience easier as you would not have to wait for customer service to look up your item. You would have the ability to find merchandise discounts, yourself, as you browse through the department store! In this session we will examine the model development, training and deployment process we used to create a discount coupon app that is executed from an edge device - your phone. Join us as we walk you through the model development and deployment lifecycle, including topics of object vision, containerizing models, data streaming and MLOps. At the end of the session, you can try the app yourself.

Kaitlyn Abdo,

Associate Technical Product Marketing Manager, Red Hat