BlogBasics Thoughts about the Nobel Prize in Physics 2024 … Prof. Dr. Christian Bauckhage, 23. October 2024 The 2024 Nobel Prize in Physics has been awarded to John Hopfield and Geoffrey Hinton for research in artificial intelligence. Find out what is behind this decision....
BlogApplication What is it capable of and what does it cost? AI for the prediction of product features Andreas Pauly, 28. June 2023 How much does my custom-made product cost? These and other factors are essential for the purchase decision for a particular manufacturer. For the latter, however, the calculation is time-consuming. Machine learning can speed up this process tremendously....
BlogBasics Automatic classification of a publication network using a Graph Attention Network Maximilian Sauerzapf, 19. May 2023 Social networks are omnipresent these days. But how can information be extracted from them with the help of neural networks? To answer this question, we present the Graph Attention Network....
BlogBasics ChatGPT: An assessment of the polarizing chatbot Prof. Dr. Christian Bauckhage, 27. January 2023 ChatGPT has been a buzzword since its release. In this series, Prof. Dr. Christian Bauckhage takes a closer look at this hype and shares his own experiences....
BlogApplication ART – Automated Tool for Generating Financial Statements Prof. Dr. Rafet Sifa, 16. March 2022 Creating financial reports takes a lot of time and is expensive. ART is a new method that should make it possible to convert structured table data from financial reports into text....
BlogResearch Contradiction detection in the German language – With machine translation and recurrent neural networks Maren Pielka, 15. December 2021 For an ML system to recognize contradictions in texts, it requires a large amount of human-like text understanding. In this article, we present models from our research that are capable of doing this....
BlogResearch Which model should I choose? Explainable model selection for time series prediction Matthias Jakobs, 06. October 2021 Selecting the model that can best solve a given problem from a set of models is often an untransparent process. For time series prediction, we present an explainable procedure for model selection. ...
BlogApplication Priority for safe Machine Learning: On the robustness of neural networks Luise Weickhmann, 14. July 2021 Hostile attacks on Machine Learning prediction models, for example in autonomous driving, could lead to great (personal) damage. Defense mechanisms can be used to protect ML models and increase their robustness against attacks. ...
BlogResearch Generative neural models learn latent probability distributions Dr. Jörg Kindermann, 16. June 2021 In this post, we explain the approach of generative neural models. These have achieved good results in application areas where hand-curated data for supervised learning is difficult or impossible to obtain....
