InDeep Consortium Meeting
| When: | Fr 20-09-2024 10:30 - 17:00 |
| Where: | House of Connections, Grote Markt 21, Groningen |
The NWO-funded InDeep project brings together pioneering researchers in the domain of interpretability of deep learning models of text, language, speech and music. Academic partners (from RUG, UvA, VU, Tilburg, and Radboud University) collaborate with various companies and non-for-profit institutions to improve the explainability of deep-learning based AI systems for a range of different tasks, and to raise awareness of the importance of AI explainability in society.
This InDeep consortium meeting will open with two invited talks by RUG researchers Daniel Herrmann (Philosophy of AI) & Yevgen Matusevych (Cognitive Plausibility of Modern LMs). It will then include research highlights from the various academic partners, a poster session on the latest research results, as well as discussions on future directions of the project.
Tentative programme
|
10.30-11.00 |
welcome coffee |
|
11.00-11.30 |
invited talk 1 by Daniel Herrmann: 'Standards for Belief Representations in LLMs' |
|
11.30-12.00 |
invited talk 2 by Yevgen Matusevych: 'Mutual exclusivity bias in visually grounded speech models' |
|
12.00-13.15 |
lunch |
|
13.15-14.00 |
intro + InDeep highlights |
|
14.00-14.45 |
project brainstorm |
|
14.45-15.15 |
coffee break |
|
15.15-16.30 |
InDeep poster session |
Participation
Participation is by invitation only.