deep learning

In the latest years, Edge AI has gained popularity and opened opportunities to bring AI applications to remote devices. Eclipse Kura, a well established IoT Edge framework, is a good candidate to apply Edge AI concepts to the real world.

In this talk we’ll demonstrate how a machine learning-based application can be easily deployed on an edge device, leveraging the Eclipse Kura features and its interoperability with the NVIDIA Triton™ Server. In particular, we’ll focus on the process of creating a deep learning anomaly detector from scratch: from data collection to training, deployment and inference on the edge.

Experience level:

Intermediate

IoT & Edge

Learning my Robot to Grasp with Promises and PushStreams

Tim Verbelen (imec)

Nowadays A.I. is the hype and everyone is talking on this awesome new neural network they trained. However, what is often overlooked is how to integrate such technology into a real system. In this talk I will show some results from our research lab on training a neural network to grasp objects. Instead of delving into the deep learning details however, I will focus on how we benefit from OSGi to integrate this onto a real robot system, and create some fancy API models using Promises and PushStreams.

Experience level:

Intermediate

OSGi

OSG(a)i: because AI needs a runtime

Tim Verbelen (imec)

Nowadays AI is reaching new heights on the hype cycle, especially due to recent advances in deep learning techniques. A lot of deep learning frameworks exist for creating and training deep neural networks, the most popular ones being PyTorch and TensorFlow. However, how to integrate, deploy and manage these neural networks in complex software systems is often overlooked. In this talk we show how OSGi can be used as a modular runtime for deep learning models. We embed those models inside OSGi bundles, and use the extender pattern to make these available as OSGi services.

Experience level:

Intermediate

OSGi