Artificial Intelligent algorithms are increasingly being implemented on-device instead of in the cloud. In this talk we will go over the advantages, disadvantages and why edge computing it is preferred in some circumstances.
An understanding is given of what is inside an edge device and how it works. Which hardware is appropriate to build and run AI algorithms. We give a broad introduction to the current edge AI landscape.
Afterwards we dig deeper and explain the what and how of enhancing edge devices by accelerating compute-intensive algorithms in hardware.
In the end we give a short workshop/demo on how to run a small Artificial Intelligent Network on an embedded device.
The speakers
Sam Sterckval earned his degree as an electronics engineer. During his
time in college, Sam found his second passion besides electronics: artificial intelligence. Quickly
he became an expert in the field of deep learning and hardware.
Throughout his electronic engineering studies, Nick Destrycker found a passion for digital chip design. In the meantime his interest in Artificial Intelligence grew. After graduation he worked as a Digital IC Designer at IMEC and ICsense.
Nick and Sam are die-hard hardware AI engineers. In an attempt to combine their passion, they founded Edgise. A venture which develops custom hardware For Edge Computing / Edge AI to efficiently run complex AI models. From off the shelf hardware to full blown custom chip design, they design what the customer needs.
Follow Us