Lamarr Lab Visits: 2025.1

Session

Trustworthy AI & Human-Centered AI

19 Feb 2025, 10:00

JvF25/3-302 - Co-Working Space (Lamarr/RC Trust Dortmund)

Conveners

Trustworthy AI & Human-Centered AI: Research Area Meeting

• Natalia Andrienko (Fraunhofer Institute IAIS)
• Jakob Rehof
• Gennady Andrienko (Fraunhofer Institute IAIS)
• Maram Akila (Lamarr / IAIS)
• Bahavathy Kathirgamanathan (Fraunhofer IAIS)

12. Welcome

Jakob Rehof

19/02/2025, 10:00

44. The Anatomy of Evidence - An Investigation into Explainable ICD Coding

Katharina Beckh

19/02/2025, 10:15

45. Directional ExplainableA AI: The Problem of the Rabbit and the Duck

Carina Newen

19/02/2025, 10:35

46. Does the model think as we expect?

Gennady Andrienko (Fraunhofer Institute IAIS), Natalia Andrienko (Fraunhofer Institute IAIS)

19/02/2025, 10:55

47. Text as parameter interactive prompt optimisation for large language models

H.S. Lin (HHU Düsseldorf)

19/02/2025, 11:15

48. From Local to Global Explanations

Maram Akila (Lamarr / IAIS)

19/02/2025, 11:45

49. Fast Linear Decomposition of ReLU Networks

A. Baudzus

19/02/2025, 12:05

50. Reinforcement Learning from Self-feedback

C. van Niekerk

19/02/2025, 12:25

51. Leveraging Human-Centered ML to create more Explainable ML models

Bahavathy Kathirgamanathan (Fraunhofer IAIS)

19/02/2025, 12:40

15. Closing

19/02/2025, 12:55

13. First Session

Presentation Session on Explainable AI

Speakers:
10:15, K. Beckh, The Anatomy of Evidence - An Investigation into Explainable ICD Coding
10:35, C.Newen, Directional ExplainableA AI: The Problem of the Rabbit and the Duck
10:55, A.& N. Andriyenko, Does the model think as we expect?
11:15, H.S. Lin, Text as parameter interactive prompt optimisation for large language models

14. Second Session

Presentation Block

Speakers List (Preliminary)
11:45, M. Akila, From Local to Global Explanations
12:05, A.Baudzus, Fast Linear Decomposition of ReLU Networks
12:25, C. van Niekerk, Reinforcement Learning from Self-feedback
12.40 B. Kathirgamanathan, Leveraging Human-Centered ML to create more Explainable ML models