tinyML Talks on January 17, 2023 “Integrate and deploy machine learning at the edge with embedded software containers” by Semir Haddad from MicroEJ

We held our next tinyML Talks webcast. Semir Haddad from MicroEJ presented Integrate and deploy machine learning at the edge with embedded software containers on January 17, 2023.

January 17 global forum

TinyML has made tremendous progress in the last few years, and many tools exist to develop and test machine learning algorithms. Yet, developers face many challenges when it comes to integrating these networks into a complete application. The neural networks become a tiny part of a more extensive system, with the complexity of sharing computing resources and memory, synchronizing events, and integrating with another code base. Deployment is another level of sophistication, with the headache of provisioning the neural network without interrupting the device’s operation. These problems are solved for edge servers and gateways using software containers and orchestration with Docker and Kubernetes. However, these cloud-native solutions are impossible for TinyML applications. Nonetheless, the same concepts are applicable. In this lecture, we will show how using embedded software containers like MicroEJ can simplify the integration and deployment of AI at the tiny edge.

Semir is the Chief Product and Strategy Officer at MicroEJ, and is in charge of product strategy and ecosystem, for the company that makes everything software defined. Semir has over 20 years of experience working with industry leaders and startups, bringing innovative technologies to industrial and consumer markets. Early in his career, he worked on digital video and audio, creating the first DVD player, and developing one of the earliest PVR software solutions for which he received four patents. At ST and Renesas he drove the creation of award winning lines of microcontrollers and microprocessors, including the STM32, RX and RZ. Recently, Semir was part of the innovators at Eta Compute that created one of the first TinyML implementation. Semir graduated from CentralSupelec with a Master of Science in Electrical and Electronics Engineering and from ESSEC/Mannheim with an MBA.

Watch on YouTube:
Semir Haddad

Download presentation slides:
Semir Haddad

Feel free to ask your questions on this thread and keep the conversation going!