Project Seminar

Project Seminar hardware for neural networks

Content

Students elaborate on a research-oriented subject in the area of hardware for neural networks. They submit a written documentation and give a presentation of the acquired advanced knowledge. They provide a set of alternative solutions to a given problem.

Organization

Project seminars do not require presence at the university and can be started at any time. If you are interested, kindly reach out directly to Prof. Dr.-Ing. Grace Li Zhang via email at grace.zhang@tu-… to check whether there is a suitable topic for you. All further information will be provided using e-mail. The following open theses are also suitable for a project seminar:

Automatic combinational circuit generation with neural networks

Exploring the Potential of Early-Exit for Efficient DNN Inference

Prerequisites

Knowledge of neural network training and inference (cf. course hardware for neural network)
Knowledge of digital or analog circuits (cf. course hardware for neural network)
Solid programming skills (either in Python or Verilog/VHDL depending on the application scenario).