28

Feb

Teaser image to Use Case for Bayesian Deep Learning in the age of ChatGPT

Use Case for Bayesian Deep Learning in the age of ChatGPT

Vincent Fortuin, Helmholtz AI & MCML

   28.02.2024

   4:15 pm - 5:45 pm

   LMU Department of Statistics and via zoom

Many researchers have pondered the same existential questions since the release of ChatGPT: Is scale really all you need? Will the future of machine learning rely exclusively on foundation models? Should we all drop our current research agenda and work on the next large language model instead?

In this talk, MCML Senior Researcher Vincent Fortuin will try to make the case that the answer to all these questions should be a convinced "no" and that now, maybe more than ever, should be the time to focus on fundamental questions in machine learning again. He will provide evidence for this by presenting three modern use cases of Bayesian deep learning in the areas of self-supervised learning, interpretable additive modeling, and neural network sparsification. Together, these will show that the research field of Bayesian deep learning is very much alive and thriving and that its potential for valuable real-world impact is only just unfolding.


Related

Link to Large-scale pretraining: the nitty-gritty details

Colloquium  •  21.02.2024  •  LMU Department of Statistics and via zoom

Large-scale pretraining: the nitty-gritty details

This talk with Robert Baldock, Aleph Alpha, will give a rare close-up of the nitty-gritty details that go into training large-scale LLMs.


Link to From Couch to Poll: Media Content and the Value of Local Information

Colloquium  •  10.01.2024  •  LMU Department of Statistics and via zoom

From Couch to Poll: Media Content and the Value of Local Information

Join the lecture with Mathias Bühler, Volkswirtschaftliche Fakultät, LMU Munich, analyzing Canada's media landscape.


Link to In Search of Alignment between Social Media Posts and Survey Responses

Colloquium  •  14.12.2023  •  LMU Department of Statistics and via zoom

In Search of Alignment between Social Media Posts and Survey Responses

Join the lecture with Frederick Conrad, Michigan Program in Survey and Data Science on thr alignment between social media's potential and survey data.


Link to AutoML for tabular datasets and tabular datasets for AutoML

Colloquium  •  06.12.2023  •  LMU Department of Statistics and via zoom

AutoML for tabular datasets and tabular datasets for AutoML

Join the lecture with our PI Matthias Feurer, LMU Munich, giving a short introduction into AutoML and an overview of the AutoML research at his chair.


Link to The power of prediction

Colloquium  •  27.11.2023  •  LMU Department of Statistics and via zoom

The power of prediction

Moritz Hardt, MPI Tübingen, explores performative prediction's impact on human populations.