Differences

This shows you the differences between two versions of the page.

--- aira:start [2026/04/09 14:28] – [Schedule Spring 2026] mtm
+++ aira:start [2026/04/16 14:27] (current) – [Schedule Spring 2026] mtm
@@ Line 21: / Line 21: @@
 ===== Schedule Spring 2026 =====
+  * **[RESEARCH TRACK] 2026.04.16**: Patrick Altmeyer,  Researcher @ Delft University of Technology, [[#section20260416|Explaining Models or Modelling Explanations? Counterfactual Explanations and Algorithmic Recourse for Trustworthy AI]]
+    * Meeting link:[[https://teams.microsoft.com/meet/372057591033533?p=u4Kxst3Eu3DsxRwxw8|MS Teams]]
+    * Recording: [[https://ujchmura.sharepoint.com/:v:/t/Section_495645_1/IQBnzx56wup2SqdgH7vcGMsTAVLulmE_zJmARUq1q1R49og?e=HHKlf1|View]]
+    * Presentation slides: {{:aira:slides-patrick-altmeyer-2026-04-16.pdf|Download}}
   * **[PHD TRACK] 2026.04.09**: Dmytro Polishchuk,  PhD Candidate @ Jagiellonian University, [[#section20260409|A Time-Aware GitHub Mining Framework for Empirical Software Quality Studies.]]
@@ Line 550: / Line 555: @@
+==== 2026-04-16 ====
+<WRAP column 15%>
+{{ :aira:patrick-altmeyer-foto.png?200| }}
+</WRAP>
+<WRAP column 75%>
+**Speaker**: Patrick Altmeyer,  Researcher @ Delft University of Technology
+**Title**: Explaining Models or Modelling Explanations? Counterfactual Explanations and Algorithmic Recourse for Trustworthy AI
+**Abstract**:
+Counterfactual explanations (CE) and algorithmic recourse (AR) have emerged as promising approaches towards explaining opaque machine learning models and empowering individuals affected by them. This seminar will explore unexpected challenges and new opportunities in this context and demonstrate how counterfactuals can be used to improve the trustworthiness of models . It will summarize some of the main findings of Patrick's Ph.D. research: https://www.patalt.org/thesis/. The slides will be made available on the website ahead of the seminar.
+**Biogram**:
+Patrick is a trained economist, computer scientist, and researcher. In his research, he has challenged long-standing paradigms in explainable AI, developed novel methods to make AI more trustworthy, and questioned hyperbolic claims about AGI. Patrick is also experienced an open-source software developer and the core developer and maintainer of Trustworthy Artificial Intelligence in Julia (Taija).
+</WRAP>
+<WRAP clear></WRAP>
 ==== 2026-04-09 ====