no code implementations • 24 Jan 2024 • Ričards Marcinkevičs, Sonia Laguna, Moritz Vandenhirtz, Julia E. Vogt
Recently, interpretable machine learning has re-explored concept bottleneck models (CBM), comprising step-by-step prediction of the high-level concepts from the raw features and the target variable from the predicted concepts.
1 code implementation • 25 Oct 2023 • Claudio Fanconi, Moritz Vandenhirtz, Severin Husmann, Julia E. Vogt
Prototype learning, a popular machine learning method designed for inherently interpretable decisions, leverages similarities to learned prototypes for classifying new data.
1 code implementation • 31 May 2023 • Moritz Vandenhirtz, Laura Manduchi, Ričards Marcinkevičs, Julia E. Vogt
We propose Signal is Harder (SiH), a variational-autoencoder-based method that simultaneously trains a biased and unbiased classifier using a novel, disentangling reweighting scheme inspired by the focal loss.