[VU ML Seminar] Next meeting: Martha Lewis

[Daza Cruz, D.F. (Daniel Fernando)]

Dear all,

We are pleased to invite you to the next meeting of the VU ML Seminar.

Next meeting we have a special guest giving a talk at the seminar: Martha Lewis, Assistant Professor of Neurosymbolic AI at the Institute of Logic, Language, and Computation (ILLC), University of Amsterdam. Her research lies at the intersection of artificial intelligence and natural language processing, with interests in compositionality, abstraction, and reasoning—particularly how concepts can be combined, generalized, and used to support reasoning in intelligent systems.

Title: Compositional approaches in modelling language and reasoning

Abstract:
Recent neural approaches to modelling language and concepts have proven quite effective, with a proliferation of large models trained on correspondingly massive datasets. However, these models still fail on some tasks that humans, and symbolic approaches, can easily solve. Large neural models are also, to a certain extent, black boxes - particularly those that are proprietary. There is therefore a need to integrate compositional and neural approaches, firstly to potentially improve the performance of large neural models, and secondly to analyze and explain the representations that these systems are using. In this talk I will present results showing that large neural models can fail at tasks that humans are able to do, and discuss alternative, theory-based approaches that have the potential to perform more strongly. I will give applications in language, reasoning, and vision. Finally, I will present some future directions in understanding the types of reasoning or symbol manipulation that large neural models may be performing.

The meeting will take place on Monday 13 April at 10:00 in room NU-3A57. We hope to see many of you there!

The organizers,

Daniel & Zhao

---
VU ML Seminar | Schedule: sites.google.com/view/vumls/home
Manage your subscription: listserver.vu.nl/mailman/options/vu.ml.seminar.beta
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://listserver.vu.nl/pipermail/vu.ml.seminar.beta/attachments/20260410/7b847b98/attachment.html>