Contact
+49 711 685 69191
+49 711 685 67900
Email
Business card (VCF)
Pfaffenwaldring 47
70569 Stuttgart
Deutschland
Room: 2.408
Subject
My field of activity includes research on energy-efficient mixed-signal neurons for artificial neural networks. Artificial neural networks have in recent years experienced an increasing spread. For decentralized use, where the computing power and the resulting power consumption is very limited, new hardware implementations are therefore required. A promising approach to increase efficiency is the analog instead of the usual digital processing of signals in the neural network.
The research work covers the design of mixed-signal neurons as well as the periphery needed for the inference of a network. Furthermore, such neural networks are investigated with respect to their trainability.
In addition, I am involved in a research association with the Institute for Robust Power Semiconductor Systems (ILH), which deals with the design of high-frequency radar systems in a 22 nm technology. Potential applications are driving assistance systems of vehicles, which are especially important for autonomous driving.
2023
- R. Nägele, J. Finkbeiner, V. Stadtlander, M. Grözing, and M. Berroth, “Analog Multiply-Accumulate Cell with Multi-Bit Resolution for All-Analog AI Inference Accelerators,” IEEE Transactions on Circuits and Systems I: Regular Papers, vol. 2023, pp. 1--13, 2023.
2022
- D. Widmann, R. Nägele, M. Grözing, and M. Berroth, “Mixed-Signal Integrated Circuit for Direct Raised-Cosine Filter Waveform Synthesis of Digital Signals Up to 24 GS/s in 22 nm FD-SOI CMOS Technology,” in IEEE International Symposium on Circuits and Systems (ISCAS), 2022, p. paper ID 1248.
- J. Finkbeiner, R. Nägele, M. Berroth, and M. Grözing, “Design of an Energy Efficient Voltage-to-Time Converter with Rectified Linear Unit Characteristics for Artificial Neural Networks,” in IEEE International New Circuits and Systems Conference (NEWCAS), 2022, pp. 327--331.
- R. Nägele, J. Finkbeiner, M. Berroth, and M. Grözing, “Design of an Energy Efficient Analog Two-Quadrant Multiplier Cell Operating in Weak Inversion,” in IEEE International New Circuits and Systems Conference (NEWCAS), 2022, pp. 5--9.
2021
- R. Nägele, F. Wiewel, S. Kelz, M. Wittlinger, M. Berroth, B. Yang, and M. Grözing, “Charge based mixed-signal multiply-accumulate circuit for energy efficient in-memory computing,” in Kleinheubacher Tagung, U.R.S.I. Landesausschuss in der Bundesrepublik Deutschland e.V, 2021, pp. 1–4.
- D. Widmann, R. Nägele, and A. Gatzastras, “140 GHz Transmitter Chip for Pseudo Random Noise Radar in 22 nm FD-SOI CMOS Technology,” in EUROPRACTICE activity report 2020 - 2021, 2021, p. 22.