DFG Research Unit 5336
Learning to Sense (L2S)
- Jointly Optimizing Sensor System Designs and Neural Networks -
The Confluence of Machine Learning and Sensor System Development
The German Research Foundation (DFG) has selected L2S as one out of eight research units in Germany that conduct dedicated fundamental research on artificial intelligence along with an interdisciplinary partner field, in our case sensor system development. For a period of four years (with a possible extension by another four years) a team of seven chairs in the Department of Electrical Engineering and Computer Science at the University of Siegen will closely collaborate on the question how to jointly develop and optimize image sensor system hardware and machine learning approaches to reach optimal performances for specific applications. Our research unit focusses on the development of novel CMOS sensors for visible light, optimal 3d microscopic setups, and optimal sub-surface THz imaging technology along with dedicated machine learning approaches in an application-specific setting. This website provides an outreach, advertises open positions, shares publications, code and data, and highlights the findings of our research unit.
Sensor System Development
We develop and optimize the next generation of CMOS Sensors, THz imaging systems, and 3d microscopes taylored to specific automatic data analysis applications.
Sensor System Simulation
In order to know how the recorded data changes as the design parameters of a sensor system are changed, we will develop faithful simulators of our three sensor modalities.
Machine Learning
We will develop new approaches to jointly optimize for the sensor system design along with neural networks parameters. New network architectures need to handle the changing type of the sensor system's data and become optimal for specific applications.
Questions?
Would you like to learn more about L2S and possible research or collaboration opportunities for you?
Feel free to contact us at michael.moeller@uni-siegen.de!