58 citations
Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- University of CambridgeGB2 papers
- University of OsloNO2 papers
- Cambridge Quantum Computing (United Kingdom)GB1 paper
- Cardiff UniversityGB1 paper
- Graz University HospitalAT1 paper
- Karolinska InstitutetSE1 paper
- Leibniz Institute for Prevention Research and Epidemiology - BIPSDE1 paper
- Medical University of ViennaAT1 paper
- Oslo University HospitalNO1 paper
- Statistics AustriaAT1 paper
- Stockholm Health Care ServicesSE1 paper
- University of BremenDE1 paper
3 papers
Solving the enigma: Enhancing faithfulness and comprehensibility in explanations of deep networks
Michail Mamalakis, Antonios Mamalakis, Ingrid Agartz +4
The accelerated progress of artificial intelligence (AI) has popularized deep learning models across various domains, yet their inherent opacity poses challenges, particularly in c…
An explainable three dimension framework to uncover learning patterns: A unified look in variable sulci recognition
Michail Mamalakis, Heloise de Vareilles, Atheer AI-Manea +8
The significant features identified in a representative subset of the dataset during the learning process of an artificial intelligence model are referred to as a 'global' explanat…
Time-dependent mediators in survival analysis: Modelling direct and indirect effects with the additive hazards model
Odd O. Aalen, Mats J. Stensrud, Vanessa Didelez +3
We discuss causal mediation analyses for survival data and propose a new approach based on the additive hazards model. The emphasis is on a dynamic point of view, that is, understa…