Sie sind hier: Startseite Forschung AI-Trust

AI-Trust

Interpretable Artificial Intelligence Systems for Trustworthy Applications in Medicine

AI-Trust
About

AI Trust is an inter- and transdisciplinary research project under the auspices of the Freiburg Institute for Advanced Studies and their Saltus! Research Group "Responsible Artificial Intelligence". The project is funded by the Baden-Württemberg Foundation.

The super-convergence of digital technologies - big data, smart sensors, artificial neural networks for deep learning, high-performance computing and other advances - enable a new generation of 'intelligent' systems, often subsumed under the notion of 'AI system'. This megatrend leads to a profound transformation of all sectors of society from education, industrial production and logistics to science and health care and poses real and imminent ethical and legal challenges. The research group AI Trust examines the challenges of Interpretable Artificial Intelligence Systems for Trustworthy Applications in Medicine

While deep learning methods offer the promise of great performance gains in various application domains, the solutions they provide are not readily comprehensible to human users. This black-box approach is acceptable in some domains, but for medical applications, transparency seems necessary so that clinicians can understand the decisions of a trained machine learning model and ultimately validate and accept its recommendations. Recently, a number of methods have been developed to provide more insight into the representations that these networks learn. So far, however, there is no systematic comparison of these methods with each other. Especially for automated EEG diagnosis, it is not clear which of these methods can provide the most helpful information for the practitioner in different circumstances. Furthermore, it is unclear to what extent these methods serve the overarching goals of interpretability, explainability, and comprehensibility. Thus, it is not clear how they may foster trust in the ‘AI-system’.

Our research project AI Trust follows an 'embedded ethics and law' approach that aims to investigate the ethical and legal challenges of a deep learning-based assistive system for EEG diagnosis ('DeepEEG' System) throughout the research and development phase in order to provide normative guidance for the development of the system. This approach intends to exemplify how the inclusion of ethical and legal expertise in developing ‘AI-systems’ in medicine may help leverage AI's innovation potential while ensuring a responsible and trustworthy 'ethics-and-law-by-design' development. More generally, this will demonstrate how the enormous societal challenges posed by ‘AI-systems’ can be framed, and the problems raised by ‘AI-systems’ can be solved from a conceptual (philosophical, ethical, legal) and a technical perspective.

 

Subproject


SP1: Transdisciplinary Conceptual Foundations: Interpretability, Explainability and Trustworthiness of DeepEEG as an AI system
(PIs: Prof. Dr. Oliver Müller, University of Freiburg, Dr. Philipp Kellmeyer, University of Freiburg Medical center, Prof. Dr. Silja Vöneky, University of Freiburg)


SP2: An interpretable deep-learning-based assistive system for EEG diagnosis (PIs: PD Dr. Tonio Ball, University of Freiburg, Jun-Prof. Dr. Joschka Boedecker, University of Freiburg, Prof. Dr. Wolfram Burgard, University of Freiburg)

SP3: Ethical, Legal and Societal Analysis of the AI-based Assistive System
(PIs: Prof. Dr. Silja Vöneky, Dr. Philipp Kellmeyer, Prof. Dr. Oliver Müller)

 

Members of the Research Group

Prof. Vöneky

Prof. Dr. Silja Vöneky

 

Institute of Public Law, Department, 2 - Public International Law and Ethics of Law, University of Freiburg

 

For more information about the person, click here.

Dr. Kellmeyer

Dr. med. Philipp Kellmeyer


Department of Neurosurgery, University of Freiburg - Medical Center

Translational Neurotechnology Lab (AG Ball)

FRIAS Saltus Responsible AI


For more information about the person, click here.

Prof. Burgard

Prof. Dr. rer. nat. Wolfram Burgard


Department of Computerscience, University of Freiburg

Autonomous Intelligent Systems Lab

FRIAS Saltus Responsible AI


For more information about the person, click here.

Prof. Müller

Prof. Dr. Oliver Müller


Department of Philosophy, University of Freiburg

Cluster of Excellence BrainLinks-BrainTools

FRIAS Saltus Responsible AI

For more information about the person, click here.

Dr. Joschka Bödecker Jun.-Prof. Dr. Joschka Bödecker


Institute for Computer Science, University of Freiburg, Neurorobotics Lab

For more information about the person, click here.
Dr. Tonio Ball

PD. Dr. Tonio Ball


Department of Neurosurgery, University of Freiburg - Medical Center,
Translational Neurotechnology Lab (AG Ball),
Bernstein Center Freiburg


For more information about the person, click here

 

 

 

Researcher

 

Daniel Feuerstack

SP3: Legal, Ethical and Societal Analysis of the AI-based Assistive System

 

For more information about the person, click here.

 

 

Selected Publications

S. Voeneky/P. Kellmeyer/O. Müller/W. Burgard (Eds.), The Cambridge Handbook of Responsible Artificial Intelligence: Interdisciplinary Perspectives, (CUP 2021, forthcoming)

T. Schmidt/S. Voeneky, A Novel Approach to Regulate AI Driven Risks, in Voeneky/Kellmeyer/Müller/Burgard (Eds), Responsible Governance of Artificial Intelligence (forthcoming 2021)
T. Schmidt, S.Vöneky, Neue Wege zur adaptiven Regulierung von Hochrisiko-KI-Technologien: Schutz von Rechten und Gemeinwohl, erschienen als FIP 3/2021

S. Voeneky, Key Elements of Responsible Artificial Intelligence – Disruptive Technologies, Dynamic Law, OdW-1/2020

S. Voeneky, Human Rights and Legitimate Governance of Existential and Global Catastrophic Risks, in Voeneky/Neuman (Eds), Human Rights, Democracy, and Legitimacy in a World of Disorder, CUP, 2018, 139-162