IPE 12-18 Bachelor and Master Theses in Physics/Electrical Engineering: Development of FPGA-based machine learning algorithms for High-Energy Physics

Karlsruhe Institute of Technology (KIT) - KIT - Helmholtz Association

Karlsruhe, Germany

Work group:

Institute for Data Processing and Electronics (IPE)


Area of research:

Diploma & Master Thesis


Job description:

Machine learning builds on ideas in computer science, statistics, and optimization. It aims on the development of algorithms to identify patterns and regularities in data, and use these learned patterns to make predictions for future observations. Boosted by its industrial and commercial applications, the field of machine learning is quickly expanding. In this thesis modern machine learning approaches, such as deep learning, should be applied to the analysis of High Energy Physics data. Current trends in FPGA design tools have made them more compatible with the high-level software making FPGAs more accessible to those who build and deploy models. Xilinx’s Zynq SoC/MPSoC appears to be an ideal platform for machine learning. Xilinx’s reVISION Stack removes traditional design barriers by allowing you to quickly take a trained network and deploy it on Zynq SoC and MPSoC for inference.

Study the Xlinix Zynq FPGA platform and its development toolsBuild up a test bench of machine learning algorithmsEstablish a workflow to implement new machine learning by Xilinx reVISION frameworkKnowledge in C and Verilog/VHDL (basic)Embedded and hardware programming (better but not required)Previous experience with developing for a Xilinx Zynq SoC (better but not required)

Contract duration

according to the study regulations

Contact person

Dr. Ing. Michele Caselle, Institute IPE
Telefon: 0721/608-25903  (michele.caselle@kit.edu)


Please apply via recruiter’s website.

Quote Reference: Helmholtz-1813

Favorite