Oberseminar "Mathematik des Maschinellen Lernens und Angewandte Analysis" - Atell Yehor Krasnopolsky
Explaining the Sensitivity Map Sparsity in Adversarially Trained Models
| Date: | 07/01/2026, 2:15 PM - 3:15 PM |
| Category: | event |
| Location: | Hubland Nord, Geb. 40, 01.003 |
| Organizer: | Lehrstuhl für Mathematik III (Maschinelles Lernen) |
| Speaker: | Atell Yehor Krasnopolsky, Universität Würzburg |
Sensitivity maps are gradient-based explainability tools used in machine learning to visualise the parts of the input most influential to a model’s decision-making. Training a model to be robust against slight perturbations of the input (adversarial training) has an effect on its sensitivity maps: they become sparser. The goal of my thesis was to mathematically answer the question: why is this the case? In this talk I will share the results.
