Highly Accurate Protein Structure Prediction with AlphaFold | SimonKohlheidelberg.ai2022-06-29 | Heidelberg AI Talk 5th of May 2022 | Highly Accurate Protein Structure Prediction with AlphaFold | Simon Kohl, DeepMind
heidelberg.aiConformal Prediction under Ambiguous Ground Truth | David Stutz (Google Deepmind)heidelberg.ai2024-05-23 | Heidelberg AI Talk from May 23rd, 2024 | Conformal Prediction under Ambiguous Ground Truth | David Stutz, Research Scientist at Google DeepMindInterpretable Vision and Language Models | Zeynep Akata (TUM)heidelberg.ai2024-05-23 | Heidelberg AI Talk from May 14th, 2024 | Interpretable Vision and Language Models | Zeynep Akata, Director of Institute for Explainable Machine Learning, Professor of Computer Science at Technical University of Munich
This talk was part of the Helmholtz Imaging Conference 2024 in Heidelberg. You can find a recap of the conference here: https://helmholtz-imaging.de/news/hi-conference-2024-recap/Building Foundation Models in Ophthamology | Pearse Keane (University College London)heidelberg.ai2024-05-23 | Heidelberg AI Talk from February 6th, 2024 | Building Foundation Models in Ophthalmology - a Clinician’s Perspective | Pearse Keane, Institute of Ophthalmology, University College London (UCL), London, UKLearning Dynamical Laws from Data | Niki Kilbertus (TUM & Helmholtz AI)heidelberg.ai2023-09-25 | Heidelberg AI Talk from September 20th, 2023 | Learning Dynamical Laws from Data | Niki Kilbertus (TUM & Helmholtz AI)Stable Diffusion and Friends - Generative Modeling in Latent Space | Robin Rombach (Stability AI)heidelberg.ai2023-02-16 | Heidelberg AI Talk February 9th, 2023 | Stable Diffusion and Friends - Generative Modeling in Latent Space | Robin Rombach (Stability AI)Human compatible World Models across Sizes, Languages and Modalities | Jonas Andrulis (Aleph Alpha)heidelberg.ai2022-11-25 | Heidelberg AI Talk 27th of September 2022 | Human compatible World Models across Sizes, Languages and Modalities; Jonas Andrulis, Constantin Eichenberg & Robert Baldock (Aleph Alpha)Why Domain Knowledge is Crucial for Machine Learning-based Medical Image Analysis | Lena Maier-Heinheidelberg.ai2021-06-23 | Heidelberg AI Talk 22nd April 2021 | Why Domain Knowledge is Crucial for Machine Learning-based Medical Image Analysis | Lena Maier-Hein, German Cancer Research Center (DKFZ)
heidelberg.aiA Brief Overview of the Success Story of Large Language Models | Timo Denkheidelberg.ai2021-06-23 | Heidelberg AI Talk 20th May 2021 | A Brief Overview of the Success Story of Large Language Models | Timo Denk, Amazon
heidelberg.aiSigned Graph Partitioning: An Important Primitive in Computer Vision | Fred Hamprechtheidelberg.ai2021-06-23 | Heidelberg AI Talk 24th March 2021 | Signed Graph Partitioning: An Important Primitive in Computer Vision | Fred Hamprecht, Heidelberg Collaboratory for Image Processing
This was a joint event with the DKFZ Data Science Seminar (https://www.dkfz.de/en/datascience/seminar.html)
heidelberg.aiFrom Development to a Certified Medical Product: Bringing AI solutions to the Patient | Philipp Mannheidelberg.ai2021-03-04 | Heidelberg AI Talk 21st October 2020 | From Development to a Certified Medical Product: Bringing AI solutions to the Patient | Philipp Mann, Mediaire
This was a joint event with the DKFZ Data Science Seminar (https://www.dkfz.de/en/datascience/seminar.html)
heidelberg.aiDeep Learning on Graphs: Successes, Challenges, and Next Steps | Michael Bronsteinheidelberg.ai2021-03-04 | Heidelberg AI Talk 7th October 2020 | Deep Learning on Graphs: Successes, Challenges, and Next Steps | Michael Bronstein, Imperial College London
This was a joint event with the DKFZ Data Science Seminar (https://www.dkfz.de/en/datascience/seminar.html)
heidelberg.aiUncertainty, Causality and Generalization | Ben Glockerheidelberg.ai2020-07-17 | Heidelberg AI Talk 8th July 2020 | Uncertainty, Causality and Generalization: Attempts to Improve Image-based Predictive Modelling | Ben Glocker, Imperial College London
This was a joint event with the DKFZ Data Science Seminar (https://www.dkfz.de/en/datascience/seminar.html)
heidelberg.aiLearning Equivariant and Hybrid Message Passing on Graphs | Max Wellingheidelberg.ai2020-06-08 | Heidelberg AI Talk 6th May 2020 | Learning Equivariant and Hybrid Message Passing on Graphs | Max Welling, University of Amsterdam
This was a joint event with the DKFZ Data Science Seminar (https://www.dkfz.de/en/datascience/seminar.html)
heidelberg.aiCross-Lingual Transfer Learning | Sebastian Ruderheidelberg.ai2020-02-25 | Heidelberg AI Talk 6th February 2020 | Cross-Lingual Transfer Learning | Sebastian Ruder, DeepMind
heidelberg.aiAnalyzing Inverse Problems in Natural Science using Invertible Neural Networks | Ullrich Kötheheidelberg.ai2019-12-20 | Heidelberg AI Talk 20th November 2019 | Analyzing Inverse Problems in Natural Science using Invertible Neural Networks | Ullrich Köthe, Visual Learning Lab, Heidelberg University
heidelberg.aiLeveraging Bayesian Uncertainty Information | Christian Leibig | heidelberg.aiheidelberg.ai2019-12-20 | Heidelberg AI Talk 21st March 2019 | Leveraging Bayesian Uncertainty Information: Opportunities and Failure Modes | Christian Leibig, MX Healthcare (Merantix)
heidelberg.aiSelf Supervision - Learning to Learn | Björn Ommer | heidelberg.aiheidelberg.ai2019-11-04 | Heidelberg AI Talk 22nd January 2019 | Self Supervision - Learning to Learn | Björn Ommer, Heidelberg University
heidelberg.aiLearning the Structure of Graph Neural Networks | Mathias Niepert | heidelberg.aiheidelberg.ai2019-07-25 | Heidelberg AI Talk 9th July 2019 | Learning the Structure of Graph Neural Networks | Mathias Niepert, NEC Labs Europe
heidelberg.aiTowards Motor Skill Learning | Jan Peters | heidelberg.aiheidelberg.ai2019-02-01 | Heidelberg AI Talk 15th January 2019 | Towards Motor Skill Learning | Jan Peters, TU Darmstadt & Max-Planck-Institute for Intelligent Systems
http://heidelberg.aiGenerative Query Networks & Neural Processes | Marta Garnelo | heidelberg.aiheidelberg.ai2018-11-28 | Heidelberg AI Talk 26th November 2018 | Generative Query Networks & Neural Processes | Marta Garnelo, Deepmind
http://heidelberg.aiHow Probabilistic Thinking and ML are Disrupting Retail | Christian Scherrer | heidelberg.aiheidelberg.ai2018-11-15 | Heidelberg AI Talk 12th November 2018 | How Probabilistic Thinking and Machine Learning are Disrupting Retail | Dr. Christian Scherrer, Principal Data Science Consultant, Blue Yonder
http://heidelberg.aiModelling Probability Distributions using Neural Networks | Christian Baumgartner | heidelberg.aiheidelberg.ai2018-11-07 | Heidelberg AI Talk 29th October 2018 | Modelling Probability Distributions using Neural Networks - Applications to Medical Imaging | Christian Baumgartner, ETH Zürich
http://heidelberg.aiDeep Learning to Solve Challenging Problems | Jeff Dean | heidelberg.aiheidelberg.ai2018-09-27 | On Tuesday, September 25th, Jeff Dean, Head of Google AI and Google Brain, visited heidelberg.ai (http://heidelberg.ai) at the German Cancer Research Center in Heidelberg:
For the past seven years, the Google Brain team has conducted research on difficult problems in artificial intelligence, on building large-scale computer systems for machine learning research, and, in collaboration with many teams at Google, on applying our research and systems to many Google products. Our group has open-sourced the TensorFlow system, a widely popular system designed to easily express machine learning ideas, and to quickly train, evaluate and deploy machine learning systems. We have also collaborated closely with Google's platforms team to design and deploy new computational hardware called Tensor Processing Units, specialized for accelerating machine learning computations. In this talk, I'll highlight some of our research accomplishments, and will relate them to the National Academy of Engineering's Grand Engineering Challenges for the 21st Century, including the use of machine learning for healthcare, robotics, and engineering the tools of scientific discovery. I'll also cover how machine learning is transforming many aspects of our computing hardware and software systems.
This talk describes joint work with many people at Google.heidelberg.ai - Deep Generative Models (Tutorial)heidelberg.ai2018-03-29 | This talk was part of our tutorial series "Advanced Deep Learning Methods for Medical Image Analysis". Jens Petersen introduced GANs and VAEs in this presentation, unfortunately the last 2-3 minutes are missing due to technical issues.