20
Mar
©jittawit.21 - stock.adobe.com
AI Keynote Series • 20.03.2025 • Online via Zoom
4:00 pm - 5:30 pm
RieszBoost: Gradient Boosting for Riesz Regression
Alejandro Schuler, Division of Biostatistics, UC Berkeley
Answering causal questions often involves estimating linear functionals of conditional expectations, such as the average treatment effect or the effect of a longitudinal modified treatment policy. By the Riesz representation theorem, these functionals can be expressed as the expected product of the conditional expectation of the outcome and the …
18
Mar
©geralt - pixabay.com
Lecture • 18.03.2025 • LMU Munich, Ludwigstr. 28 VG/II; Room 211b
10:30 am - 11:30 am
Leveraging Predictive Uncertainty to Enable Reliable Deployment of AI Models
Florian Buettner, Goethe-University Frankfurt
This talk explores a unified theoretical framework for uncertainty quantification in machine learning, extending traditional methods to modern applications like generative modeling. By generalizing the bias-variance decomposition using proper scores, it introduces Bregman Information as a key component for epistemic uncertainty estimation. The …
17
Mar
Lecture • 17.03.2025 • AI for Good Platform (Online)
4:00 pm - 5:00 pm
Explainable Multimodal Agents With Symbolic Representations & Can AI Be Less Biased?
Our Junior Member Ruotong Liao at United Nations AI for Good
Our junior member Ruotong Liao is an invited speaker at the United Nations “AI for Good”! With her talk “Perceive, Remember, and Predict: Explainable Multimodal Agents with Symbolic Representations,” Ruotong Liao will participate in the online event “Explainable Multimodal Agents with Symbolic Representations & Can AI be less biased?” hosted by …
17
Mar
©Elliott Wu
Talk • 17.03.2025 • 02.09.023 TUM Campus Garching, Boltzmannstrasse 3
2:00 pm - 5:00 pm
From Pixels to 3D Motion: Recreating the Physical Natural World From Images
Elliott (Shangzhe) Wu, University of Cambridge
On Monday, March 17th, 2025 at 2pm, Prof. Dr. Elliott (Shangzhe) Wu is visiting us from the University of Cambridge and giving a talk. You can sign up for 1-on-1 meetings with him here. Pixel-based generative models nowadays excel at creating compelling images, but often struggle to preserve basic physical properties, such as shape, motion, material, …
07
Mar
BMBF Event • 07.03.2025 • BMBF Berlin, Kapelle-Ufer 1, 10117 Berlin
10:00 am - 1:00 pm
Technologie von morgen, Probleme von gestern? Was tun gegen den Gender Gap in der Künstlichen Intelligenz?
BMBF Event on International Women’s Day 2025
The central event of the Federal Ministry of Education and Research (BMBF) on International Women’s Day 2025 will focus on the gender gap in AI and ask: “Tomorrow’s technology, yesterday’s problems? What to do about the gender gap in AI?” In addition to a keynote speech, a moderated panel discussion is planned in which experts from science, research …
18
Feb
Munich AI Lectures • 18.02.2025 • Senatssaal, Geschwister-Scholl-Platz 1, Ludwig-Maximilians-Universität München
5:00 pm - 6:30 pm
Unveiling the Cosmos: Deep Learning Solutions to Inverse Problems in Astrophysics
Prof. Dr. Jean-Luc Starck, CEA-Saclay, France
Join us for the next Munich AI Lectures featuring Prof. Dr. Jean-Luc Starck from the CosmoStat Laboratory, CEA CEA-Saclay, France. Prof. Starck will present “Unveiling the Cosmos: Deep Learning Solutions to Inverse Problems in Astrophysics.”
The lecture will explore how deep learning is transforming the analysis of astrophysical inverse problems, …
13
Feb
©jittawit.21 - stock.adobe.com
AI Keynote Series • 13.02.2025 • Online via Zoom
10:00 am - 11:30 am
Simplifying Debiased Inference via Automatic Differentiation and Probabilistic Programming
Alex Luedtke, Department of Statistics, University of Washington
The speaker would introduce an algorithm that simplifies the construction of efficient estimators, making them accessible to a broader audience. ‘Dimple’ takes as input computer code representing a parameter of interest and outputs an efficient estimator. Unlike standard approaches, it does not require users to derive a functional derivative known …
13
Feb
Virtual Workshop on Generative AI with Diffusion Models • 13.02.2025 • Virtual
9:00 am - 5:00 pm
Generative AI With Diffusion Models
Virtual Workshop From Nvidia
Generative AI plays a significant role across industries. In this course, learners will take a deeper dive into denoising diffusion models.
12
Feb
Virtual Workshop on Data Science with RAPIDS • 12.02.2025 • Virtual
9:00 am - 5:00 pm
Fundamentals of Accelerated Data Science With RAPIDS
Virtual Workshop From Nvidia
In this workshop, you’ll learn how to build and execute end-to-end GPU-accelerated data science workflows. Using the RAPIDS™-accelerated data science libraries, you’ll apply a wide variety of GPU-accelerated machine learning algorithms for data analysis.