What if you had a magic wand that could help you do your everyday chores? With the rise of magical AI systems like ChatGPT is this becoming a reality? Other than creating some basic code, writing tv scripts and generally scaring society a little, what else could this magic be used for?
Moving AI models from development to production has its own set of challenges and risks when the Edge is involved.
In this laboratory we're going to learn how to overcome these challenges leveraging the Nvidia Triton™ Inference Server, Eclipse Kura and Eclipse Kapua, two frameworks for the Edge and Cloud.
This laboratory will give attendees a hands-on experience of the entire lifecycle of an Edge AI application, from data collection to training to model deployment.
AI software and hardware advancements are resulting in a flood of smart interactive devices that can recognize and react to sights, sounds, and other environmental stimuli while executing much of the processing at the edge and so not requiring a constant internet connection. We will report on the activities of the Oniro project to develop a modern AI-supporting operating system that allows for the quick and easy integration of ready-to-use AI components, as well as its ability to interact with other available frameworks such as OpenHarmony and other opensource distributions.
COVID-19 has been a terrible blight upon the world. It has also greatly accelerated the adoption and transformation of digital technologies, especially around open source, cloud, and AI. Around the world, including in Europe and in China, there are also large new investments into digital technologies to spur economic recovery, such as Next Generation EU.
This presentation will discuss the future of digital technologies and the policies that will shape them in this COVID-19 era. And, it will also consider why there is good reason to hope for recovery based on these trends.
Akraino KubeEdge blueprint project builds real world Edge computing user cases based on KubeEdge. The first case of this project is ML Offloading. With Artificial Intelligence democratized into mobile phones, the computing resource limitation of mobile devices is increasingly a concern. More and more apps running on mobile phones have to offload ML related operations, starting with the public cloud. Offloading to edge is a natural thought for latency and data security considerations.
Abstract:
The Internet of Things and Artificial Intelligence are undoubtedly key elements on the stony path to Digital Transformation and future software development. Both are not new but technical reality for our projects and products over decades. However, the new feature is the scaling effect of IoT and AI explosively penetrating the software world.
Teaser: Today, the development of automotive software functions based on artificial intelligence still needs a lot of different tools, languages and frameworks.
In this talk, we introduce how we built upon the Eclipse eco-system an integrated development environment called "DAISY" (Development environment for Artificial Intelligence SYstems).
