tinyML Talks: AIfES – an open-source standalone AI framework for almost any hardware

In the last few years there have been more and more solutions for running machine learning (ML) on microcontrollers. Some of the most popular are scaled down versions of frameworks designed for servers. But those are only suitable for fairly powerful MCUs.

This is now a thing of the past. With the open-source solution AIfES (Artificial Intelligence for Embedded Systems) from the Fraunhofer Institute for Microelectronic Circuits and Systems (IMS) it’s possible to run, and even train, artificial neural networks (ANN) on almost any hardware, including 8-bit microcontrollers. To be able to try AIfES directly, it has been released for the amazing Arduino IDE as a library and can be used with any Arduino or Arduino compatible board.
AIfES inventor and product manager Pierre Gembaczka will introduce the framework and will also show an on-device training live demo. The new features of the upcoming update will also be shown.

Date

December 1, 2021

Location

Virtual

Contact us

Discussion

Schedule

Timezone: PST

AIfES – an open-source standalone AI framework for almost any hardware

Pierre GEMBACZKA, Program manager

Fraunhofer IMS

In the last few years there have been more and more solutions for running machine learning (ML) on microcontrollers. Some of the most popular are scaled down versions of frameworks designed for servers. But those are only suitable for fairly powerful MCUs.

This is now a thing of the past. With the open-source solution AIfES (Artificial Intelligence for Embedded Systems) from the Fraunhofer Institute for Microelectronic Circuits and Systems (IMS) it’s possible to run, and even train, artificial neural networks (ANN) on almost any hardware, including 8-bit microcontrollers. To be able to try AIfES directly, it has been released for the amazing Arduino IDE as a library and can be used with any Arduino or Arduino compatible board.
AIfES inventor and product manager Pierre Gembaczka will introduce the framework and will also show an on-device training live demo. The new features of the upcoming update will also be shown.

Pierre GEMBACZKA, Program manager

Fraunhofer IMS

Dr. Pierre Gembaczka is Program-manager at Fraunhofer IMS. He studied Microtechnology and medical technology and holds a Master degree from the University of Applied Sciences in Gelsenkirchen. Afterwards he completed his doctorate at the Fraunhofer IMS in cooperation with the University of Duisburg Essen and obtained the academic degree of a doctor of engineering. From 2014 to 2017 he worked as a research assistant in the department Micro- and Nanosystems – Pressure Sensors at Fraunhofer IMS. From 2018 to 2020 he works as research assistant in the embedded systems group at Fraunhofer IMS and researches embedded AI solutions for various applications. He is inventor of the AI software framework AIfES (Artificial Intelligence for Embedded Systems). Since May 2020 he is Program manager “Industrial AI” and AIfES Product Manager.

Schedule subject to change without notice.