XMANAI: Explainable Artificial Intelligence for Manufacturing
News from Nov. 10, 2020
What is artificial intelligence (AI) and how does it work? For many people, these questions are not easy to answer: this is due to the fact that many machine learning and deep learning algorithms can not be examined after their execution. The just started EU-funded XMANAI project will focus on explainable AI, a concept that contradicts the idea of the “black box“ in machine learning, where even the designers can not explain why the AI reaches at a specific decision.
Moving from “black box“ to “glass box“: The research project XMANAI aims at placing the indisputable power of Explainable AI at the service of manufacturing and human progress, carving out a “human-centric”, trustful approach that is respectful of European values and principles, and adopting the mentality that “our AI is only as good as we are”. XMANAI, demonstrated in 4 real-life manufacturing cases, will help the manufacturing value chain to shift towards the amplifying AI era by coupling (hybrid and graph) AI “glass box” models that are explainable to a “human-in-the-loop” and produce value-based explanations, with complex AI assets (data and models) management-sharing-security technologies to multiply the latent data value in a trusted manner, and targeted manufacturing apps to solve concrete manufacturing problems with high impact.
Fraunhofer FOKUS is the leader of the work package “Asset Management Bundles Methods and System Designs“, which will define the main assets (data and models) management and sharing methods that will be integrated into the XMANAI platform focusing more on operations that are typically performed by data engineers and of business experts when it comes to data identification and collection. Dr. Yury Glikman, deputy director of business unit Digital Public Services at Fraunhofer FOKUS, is the scientific coordinator of FOKUS‘ work package.
The research project involves 15 partners from 7 different countries and is funded by European Commission within the research programme Horizon 2020. Project coordinator is the Italian company TXT E-SOLUTIONS S.P.A. XMANAI started on November 1st, 2020 and runs until April 30, 2024.