EVENT

Event News

Talk on " AI and IoT: processing chain and examples -- Embedded systems for AI" by Prof. Christophe Cerin (CNRS, Sorbonne Paris Nord University)

We are pleased to inform you about the upcoming seminar by Prof. Christophe Cerin (CNRS, Sorbonne Paris Nord University) titled:"AI and IoT: processing chain and examples -- Embedded systems for AI" Everyone interested is cordially invited to attend!

Title:

AI and IoT: processing chain and examples -- Embedded systems for AI

Abstract:

In this presentation, we will imagine that we have to build a model of what is happening in a building equipped with sensors (temperature, CO2, etc.). We will force ourselves to calculate this model on embedded devices (ESP32 for example) and, for confidentiality reasons, we will not take the data produced by the sensors out of the building. We will discuss some online learning algorithms, embedded technologies and the current capabilities of "chips" to run small pre-trained models. We will also discuss model reduction techniques (quantization, pruning, etc.) which are essential when using resource-constrained hardware (a single computing core, a few megabytes of RAM). We will suggest, for students, model reduction manipulations and we will assess the quality of the inferences obtained from these models. We could then conclude, who knows, that "Small is beatiful" and that AI at the edge of the network is effective.

Speaker Bio:

Christophe Cérin is a Computer Science Professor at Sorbonne Paris Nord University since 2005, focusing on high-performance computing, including grid, cloud, and edge computing. He develops middleware, algorithms, and tools for distributed system management and explores computing's environmental impact. As an IEEE Member, he received the 2020 IEEE Technical Committee on Cloud Computing Research Innovation Award. He serves on the IEEE Transactions on Computers editorial board and as Associate Editor for Springer's Journal of Cloud Computing. Starting September 2021, he joined Grenoble University for research with the Edge Intelligence program and INRIA Datamove team (Delegation INRIA programme). He recently chaired the FogSLA project on Fog orchestration and has industrial experience with the Wolphin, Wendelin, and Resilience projects related to cloud and big data.