Corrosion causes over US $2.5 trillion in annual economic losses, driving the need for protective polymer coatings that combine barrier effectiveness with active inhibition. Conventional ex‐situ mixing MOFs into polymer matrices often suffer from particle aggregation and poor interfacial adhesion, resulting in loca...
Bhavesh M. Patil, Paresh M. Patil, Jayashree N. Kudalkar et al.· Materials and Corrosion· 0 citations
This work reframe shortcut auditing as a decomposition of the variance of intermediary representations with Independent Canonical cONcepts (ICON), which separates learned shortcuts from merely correlated concepts, which it confirms with independent validation checks.
R. Rane, Marco Simnacher, Manuel Pfeuffer et al.· 0 citations
Deep neural networks often exploit spurious associations, a failure known as shortcut learning. Before deployment, models should be audited for reliance on a set of concepts, such as acquisition artifacts or demographics. Current methods, such as linear probes and concept activation vectors, measure reliance by asking...
R. Rane, Marco Simnacher, Manuel Pfeuffer et al.· 0 citations
It is argued that intervention-based robustness tests should become standard for trustworthy clinical speech models and show that high predictive performance and the absence of a significant diagnostic-group difference in a measured acoustic factor are not sufficient for robustness.
Serli Kopar, Alkis Koudounas, R. Rane et al.· 0 citations
The findings suggest that robust, individualized brain-based predictions for mental health outcomes remain challenging with the available data and sample size.
Marija Tochadse, Julia Klawohn, Christian Kaufmann et al.· Scientific Reports· 0 citations
This work introduces an estimation procedure that refits the final layer of a pre-trained network to include covariate effects, and shows how these effects can be orthogonalised with respect to covariates to exclude their mediated effects and that model predictions can be marginalised over the covariate distribution to...
Manuel Pfeuffer, R. Rane, Kerstin Ritter et al.· 0 citations
CON decomposition is introduced, which quantifies how much of a layer's variance each concept explains given all other concepts and the outcome, and how much none of them explains, yielding layer-comparable, calibrated scores that suppress false positives.
Roshan Prakash, Marco Simnacher, Manuel Pfeuffer et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
