"visIT" science journal: Insight into our current research

In "visIT", our science journal or theme brochure, we inform you in a concentrated form about current focal topics of our research. On this webpage, you can find all issues in digital form (mainly in German language). If you wish, we will be happy to add you to the distribution list for the digital or print edition - you will then receive visIT two to three times a year, free of charge. Simply write an e-mail to: publikationen@iosb.fraunhofer.de

 

The four-page newsletter InfOSB, which informs about recent developments in all the institute's business units (in German), accompanies visIT. visIT subscribers receive it automatically.

Current visIT issue: Explainable AI in practice

Artificial intelligence (AI) can support humans in a variety of ways, for example in optimizing industrial production processes, in driving or in medicine in the selection of therapy options. As AI solutions play an increasingly important role in everyday life, ethical principles - such as those described by the EU in the AI Act currently being negotiated - are important cornerstones for their development. Not least in order to observe these principles, traceability and transparency of AI models are important: they support the development of AI models and strengthen trust in AI results.

A long tradition in AI is inherently comprehensible white-box models such as small decision trees or simple Bayesian networks. Their simple and clear structure makes it possible to directly understand algorithmic relationships.

For more than ten years, methods from the field of machine learning, in particular deep learning, have come into focus. These are trained on large amounts of data and provide AI models of high quality for specific tasks. Such models are very complex; we cannot intuitively penetrate their approach. They are therefore referred to as black boxes. So-called explanatory models from the Explainable Artificial Intelligence (XAI) research area make it possible to better understand the processes in the black box. These can be developed explicitly for specific AI models or generally for different AI models. Explanations are generated across the entire AI model or for specific AI outcomes. The use of specially developed procedures for user interface design and usability engineering ensures optimal usability.

Fraunhofer IOSB masters the development of AI solutions and associated explanatory models and applies them in different application areas. As a partner for SMEs and industry, we are happy to bring this experience to your use case. In this visIT, we provide insight into concrete XAI use cases from the areas of quality assurance and production, sensor-based reconnaissance and surveillance, and medicine. Finally, we present our XAI toolbox, which enables us to generate various explanations for your AI process as well - and thus ensure targeted development, trust and transparency in your application as well.

We hope you enjoy reading our issue "Explainable AI in Practice".

© Fraunhofer IOSB

Content

The links will take you directly to the corresponding page of the ePaper (in German):

Further editions

 

visIT Laser, Quantum Technology & Active Sensor Systems

In this issue: lasers, photonic quantum technology, quantum physics, and active optronic sensing.

 

visIT AI Systems Engineering

This issue focuses on the exciting and forward-looking topic of AI Systems Engineering!

 

visIT Sensor Data and Smart City

In this issue we want to look at the Smart City topic in the context of open sensor data standards.

 

visIT Smart Agriculture

In this issue of the Science-Journal visIT Fraunhofer IOSB's solution approaches to the topic of Smart Aggriculture are presented.

 

visIT AI for Defence Applications

This issue provides insights into developments and results on AI technologies in defence technology.

 

visIT Industrial IoT und Edge Computing

This issue presents intelligent production processes for quality assurance and secure data exchange on IoT platforms.

 

visIT AI for Autonomous Systems and Assistance Applications

In this issue: Artificial intelligence in use for toxic waste removal and in assistance applications.

 

visIT Intelligent Safety Technology

This visIT highlights a selection of topics in the context of security technologies. Concrete applications as well as ongoing research work are explained.

 

visIT Privacy by Design and IT Security

Privacy by design and IT security are elementary for new technologies. In this visIT issue you can learn more about data protection and IT security in systems.

 

visIT Energy, Water and Environment business unit

Energy transition demands new solutions. In this issue, we present technologies ranging from Digitalization to IT security.

 

visIT Mobile Robot Systems

The current issue of our themed magazine visIT is dedicated to approaches that increase the degree of autonomy of robotic systems.

 

visIT Industrial IoT – Digital Twin

In the visIT issue “Industrial IoT – Digital Twin“ (in English) we take a closer look at the current trends in automation.

 

visIT Recycling

“Recycling is the largest source of raw materials in the world“. This issue of visIT highlights how innovative projects at Fraunhofer IOSB are helping to develop and optimise new recycling cycles.

 

visIT Public Safety

The new issue of Fraunhofer IOSB sheds light on various facets of the topic “Public Safety“.

 

visIT Industrie 4.0

The new Fraunhofer IOSB issue highlights various facets of the “Industry 4.0“ topic area

 

visIT Autonomous Mobility

The new issue of Fraunhofer IOSB highlights different facets of the topic “Autonomous Mobility“.