Raphael Nägele

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.