Interpretability

IML member at Software Campus: Interpretability in Unsupervised Machine Learning: Local and Model-Agnostic Explanations

The Software Campus is a prestigious training program for master’s and doctoral students in computer science, preparing them for leadership roles. The program, supported by the Federal Ministry of Education and Research, is a collaboration between 21 universities, research institutions, and companies. Participants lead their own IT research project, managing Read more…

By Franziska Scheurer, ago

Comprehensive Evaluation of
Feature Attribution Methods in Explainable AI via Input Perturbation

Explainable AI (XAI) has demonstrated its potential in deciphering discriminatory features in machine learning (ML) decision-making processes. Specifically, XAI’s feature attribution methods shed light on individual decisions made by ML models. However, despite their visual appeal, these attributions can be unfaithful. To ensure the faithfulness of feature attributions, it is Read more…

By Franziska Scheurer, ago