Dr.-Ing.

Schneider, Daniel

Filters
2
2
Reset filters

Settings
Now showing 1 - 2 of 2
  • Publication
    StaDRe and StaDRo: Reliability and Robustness Estimation of ML-Based Forecasting Using Statistical Distance Measures
    ( 2022)
    Akram, Mohammed Naveed
    ;
    Ambekar, Akshatha
    ;
    Sorokos, Ioannis
    ;
    Aslansefat, Koorosh
    ;
    Schneider, Daniel
    Reliability estimation of Machine Learning (ML) models is becoming a crucial subject. This is particularly the case when such models are deployed in safety-critical applications, as the decisions based on model predictions can result in hazardous situations. In this regard, recent research has proposed methods to achieve safe, dependable, and reliable ML systems. One such method consists of detecting and analyzing distributional shift, and then measuring how such systems respond to these shifts. This was proposed in earlier work in SafeML. This work focuses on the use of SafeML for time series data, and on reliability and robustness estimation of ML-forecasting methods using statistical distance measures. To this end, distance measures based on the Empirical Cumulative Distribution Function (ECDF) proposed in SafeML are explored to measure Statistical-Distance Dissimilarity (SDD) across time series. We then propose SDD-based Reliability Estimate (StaDRe) and SDD-based Robustness (StaDRo) measures. With the help of a clustering technique, the similarity between the statistical properties of data seen during training and the forecasts is identified. The proposed method is capable of providing a link between dataset SDD and Key Performance Indicators (KPIs) of the ML models.
  • Publication
    The Concept of Ethical Digital Identities
    ( 2022)
    Cioroaica, Emilia
    ;
    Buhnova, B.
    ;
    Jacobi, F.
    ;
    Schneider, Daniel
    Dynamic changes within the cyberspace are greatly impacting human lives and our societies. Emerging evidence indicates that without an ethical overlook on technological progress, intelligent solutions created to improve and enhance our lives can easily be turned against humankind. In complex AI-socio-technical ecosystems where humans, AI (Artificial Intelligence) and systems interact without a common language for building trust, this paper introduces a methodological concept of Ethical Digital Identities for supporting the ethical evaluation of intelligent digital assets.