Birds look like cars: adversarial analysis of intrinsically interpretable deep learning
Sign Up to like & getrecommendations! Published in 2025 at "Machine Learning"
DOI: 10.1007/s10994-025-06896-w
Abstract: A common belief is that intrinsically interpretable deep learning models ensure a correct, intuitive understanding of their behavior and offer greater robustness against accidental errors or intentional manipulation. However, these beliefs have not been comprehensively… read more here.
Keywords: interpretable deep; deep learning; learning; intrinsically interpretable ... See more keywords
Magnetoencephalography Decoding Transfer Approach: From Deep Learning Models to Intrinsically Interpretable Models
Sign Up to like & getrecommendations! Published in 2024 at "IEEE Journal of Biomedical and Health Informatics"
DOI: 10.1109/jbhi.2024.3365051
Abstract: When decoding neuroelectrophysiological signals represented by Magnetoencephalography (MEG), deep learning models generally achieve high predictive performance but lack the ability to interpret their predicted results. This limitation prevents them from meeting the essential requirements of… read more here.
Keywords: deep learning; knowledge; learning models; interpretable models ... See more keywords