1 - 10 of 533
-
PublicationA global scale comparison of risk aggregation in AI assessment frameworks( 2024-05-06)AI applications bear inherent risks in various risk dimensions, such as insufficient reliability, robustness, fairness or data protection. It is well-known that trade-offs between these dimensions can arise, for example, a highly accurate AI application may reflect unfairness and bias of the real-world data, or may provide hard-to-explain outcomes because of its internal complexity. AI risk assessment frameworks aim to provide systematic approaches to risk assessment in various dimensions. The overall trustworthiness assessment is then generated by some form of risk aggregation among the risk dimensions. This paper provides a systematic overview on risk aggregation schemes used in existing AI risk assessment frameworks, focusing on the question how potential trade-offs among the risk dimensions are incorporated. To this end, we examine how the general risk notion, the application context, the extent of risk quantification, and specific instructions for evaluation may influence overall risk aggregation. We discuss our findings in the current frameworks in terms of whether they provide meaningful and practicable guidance. Lastly, we derive recommendations for the further operationalization of risk aggregation both from horizontal and vertical perspectives.
-
PublicationOn the effects of biased quantum random numbers on the initialization of artificial neural networks( 2024-01-16)Recent advances in practical quantum computing have led to a variety of cloud-based quantum computing platforms that allow researchers to evaluate their algorithms on noisy intermediate-scale quantum devices. A common property of quantum computers is that they can exhibit instances of true randomness as opposed to pseudo-randomness obtained from classical systems. Investigating the effects of such true quantum randomness in the context of machine learning is appealing, and recent results vaguely suggest that benefits can indeed be achieved from the use of quantum random numbers. To shed some more light on this topic, we empirically study the effects of hardware-biased quantum random numbers on the initialization of artificial neural network weights in numerical experiments. We find no statistically significant difference in comparison with unbiased quantum random numbers as well as biased and unbiased random numbers from a classical pseudo-random number generator. The quantum random numbers for our experiments are obtained from real quantum hardware.
-
-
PublicationRechtliche Fairnessanforderungen an KI-Systeme und ihre technische Evaluation( 2024)Im vorliegenden Beitrag werden rechtliche Fairness-Anforderungen an KI-Systeme anhand ausgewählter Kreditscoring-Systeme beleuchtet. Einerseits wird das geltende Recht in den Blick genommen und insbesondere die Frage einer mittelbaren Drittwirkung des Art. 3 GG im Kontext des Kreditscorings erörtert. Andererseits wird auch ein Fokus auf die zukünftige europäische KI-Verordnung (KI-VO) gelegt. Mittels einer juristisch-informatischen Analyse werden Ansätze zur Interpretation und Operationalisierung der fairnessbezogenen Anforderungen an die verwendeten Daten gem. Art. 10 KI-VO nach dem Stand der Technik diskutiert. Diese werden sodann exemplarisch anhand eines konkreten Kreditscoring-Beispiels evaluiert. Der Beitrag schließt mit Empfehlungen hinsichtlich ausgewählter rechtlicher Rahmenbedingungen für einen "fairen" KI-Einsatz.
-
PublicationWasserstein Dropout( 2024)Despite of its importance for safe machine learning, uncertainty quantification for neural networks is far from being solved. State-of-the-art approaches to estimate neural uncertainties are often hybrid, combining parametric models with explicit or implicit (dropout-based) ensembling. We take another pathway and propose a novel approach to uncertainty quantification for regression tasks, Wasserstein dropout, that is purely non-parametric. Technically, it captures aleatoric uncertainty by means of dropout-based sub-network distributions. This is accomplished by a new objective which minimizes the Wasserstein distance between the label distribution and the model distribution. An extensive empirical analysis shows that Wasserstein dropout outperforms state-of-the-art methods, on vanilla test data as well as under distributional shift in terms of producing more accurate and stable uncertainty estimates.
-
PublicationAutomatic scoring of Rhizoctonia crown and root rot affected sugar beet fields from orthorectified UAV images using Machine Learning( 2024)Rhizoctonia crown and root rot (RCRR), caused by Rhizoctonia solani, can cause severe yield and quality losses in sugar beet. The most common strategy to control the disease is the development of resistant varieties. In the breeding process, field experiments with artificial inoculation are carried out to evaluate the performance of genotypes and varieties. The phenotyping process in breeding trials requires constant monitoring and scoring by skilled experts. This work is time demanding and shows bias and heterogeneity according to the experience and capacity of each individual person. Optical sensors and artificial intelligence have demonstrated a great potential to achieve higher accuracy than human raters and the possibility to standardize phenotyping applications. A workflow combining red-green-blue (RGB) and multispectral imagery coupled to an unmanned aerial vehicle (UAV), and machine learning techniques was applied to score diseased plants and plots affected by RCRR. Georeferenced annotation of UAV orthorectified images. With the annotated images, five convolutional neural networks were trained to score individual plants. The training was carried out with different image analysis strategies and data augmentation, respectively. The custom convolutional neural network trained from scratch together with a pre-trained MobileNet showed the best precision in scoring RCRR (0.73 to 0.85). The average per plot of spectral information was used to score plots, and the benefit of adding the information obtained from the score of individual plants was compared. For this purpose, machine learning models were trained together with data management strategies, and the best-performing model was chosen. A combined pipeline of Random Forest and k-Nearest neighbors have shown the best weighted precision (0.67). This research provides a reliable workflow for detecting and scoring RCRR based on aerial imagery. RCRR is often distributed heterogeneously in trial plots, therefore, considering the information from individual plants of the plots showed a significant improvement of UAV based automated monitoring routines.
-
PublicationShort-term predictor for COVID-19 severity from a longitudinal multi-omics study for practical application in intensive care units( 2024)
-
PublicationEinsatz von KI-basierten Anwendungen durch Krankenhauspersonal: Aufgabenprofile und Qualifizierungsbedarfe( 2024)
-
PublicationUsing ScrutinAI for visual inspection of DNN performance in a medical use case( 2024)
-
PublicationDeep reinforcement learning in service of air traffic controllers to resolve tactical conflicts( 2024)Dense and complex air traffic requires higher levels of automation than those exhibited by tactical conflict detection and resolution (CD&R) tools that air traffic controllers (ATCOs) use today: AI tools can act on their own initiative, increasing the capacity of ATCOs to control higher volumes of traffic. However, given that the air traffic control (ATC) domain is safety critical, requires AI systems to which ATCOs are comfortable to relinquishing control, guaranteeing operational integrity and automation adoption. Two major factors towards this goal are quality of solutions and operational transparency. ResoLver, the system that this article presents, addresses these challenges using an enhanced graph convolutional reinforcement learning method operating in a multiagent setting where each agent – representing a flight – performs a CD&R task, jointly with other agents. We show that ResoLver can provide high-quality solutions with respect to stakeholders interests (air traffic controllers and airspace users), addressing also operational transparency issues, which have been validated by ATCOs in simulated real-world settings.
