Dear dida follower,
In our newsletter we would like to inform you about exciting news at dida.
Our highlight of the last months was certainly the dida conference, which we organized at the end of April on the occasion of our 5th anniversary in Berlin. More than 200 guests had the opportunity to exchange ideas on the topic of Machine Learning during exciting and diverse presentations and workshops. We captured the day in this video - the individual presentations can be viewed here. We would like to thank all participants for a great conference!
Regarding our research projects, we are pleased to report progress. In particular, we would like to point out the following scientific publications:
Within the project "CropClass" the paper "Early Crop Classification via Multi-Modal Satellite Data Fusion and Temporal Attention" has been published in the MDPI Journal on Remote Sensing.
The paper "Deep learning based visual inspection of facets and p-sides for efficient quality control of diode lasers" originates from the project "LaserSKI" and investigates defect detection using Deep Learning. It has been published in the Proceedings of the SPIE conference.
At ICML 2023, we were represented by the paper "Improved sampling via learned diffusions", which advances approaches from the field of diffusion-based generative modeling.
We look forward to continuing to actively contribute to current scientific AI developments.
Finally, we would like to point out three of our current projects. The first two are from the area of production optimization.
In collaboration with Cylad, we analyzed time series data of a base metal cleaning process using machine learning. In particular, we optimized process parameters and were able to increase operational performance because our solution can predict and minimize impurities.
The "AIgent3D" project is about AI-based nozzle contamination detection in industrial 3D printing. Based on infrared images of 3D printers, we have developed a classification algorithm that detects dirty glands to optimize production processes in 3D printing.
The third is a funded project, which we will tackle together with our partners Ostfalia University of Applied Sciences, A&B Peine and GE-T.
Last but not least, we would like to point out that you are welcome to contact us - as usual - if you would like to talk about current AI topics, such as generative AI or large language models - in both areas we have been able to gather exciting practical experience in the last months.
We would like to thank our customers and partners for the very pleasant cooperation and look forward to the next months.
Best regards
Philipp Jackmuth & Dr. Lorenz Richter
