Navigation and service

Advertising division: ZEA-2 - Electronic Systems
Reference number: 2020M-048, Electrical engineering or physics

Master Thesis: Reservoir Computing using Coupled Oscillators

The Central Institute of Engineering, Electronics and Analytics – Electronic Systems (ZEA-2) is a scientific engineering institute of Forschungszentrum Jülich GmbH performing research and development projects in close cooperation with the institutes of the research center as well as external partners. The focus of our work is electronic and information technology system solutions in sensor and detector technology, signal and data processing as well as measurement techniques.

Project Description:
This project is running within the third-party funded “Advanced Computing Architecture” project in Forschungszentrum Jülich GmbH, aiming towards multi-scale natural-density Neuromorphic Computing systems (www.fz-juelich.de/aca). Artificial recurrent neural networks (RNN) dominate a large class of computational models within applications ranging from machine learning to modeling biological brain and computational neuroscience. Despite their widely acknowledged potential and computational power, RNN’s, however, remain insufficient during learning process. For overcoming these difficulties, reservoir computing has been proposed as a paradigm shift in RNN training. It’s shown that any substrate with echo state property can be used as a reservoir, namely a network of coupled oscillators (or even a bucket of water!).

Your Tasks:
In the framework of this project, within the existing theories a reservoir of coupled electrical oscillators should be developed. Realization of an ensemble of electrical oscillators, encoding/decoding the digitized data into phase/frequency domain , and the programmable coupling of the oscillators using existing digital platforms (e.g. FPGA) are among the realization possibilities.

Your Profile:

  • Electrical Engineering or Computer science student
  • Knowledge in hardware design as prerequisite is an advantage
  • Knowledge in different programming languages
  • Experience in neural networks is an advantage
  • Willingness to work in team is prerequisite

Our Offer:

  • Opportunity to work together in a team of highly motivated scientists and technicians
  • Further development of your personal abilities in connection with a socially balanced work environment
  • Strongly supported on-the-job training at the start

Forschungszentrum Jülich GmbH aims to employ more women in this area and therefore particularly welcomes applications from women.

Application
Did we raise your attention and you got curious?
We are looking forward for your application.
For further information please contact:

Forschungszentrum Jülich GmbH
Central Institute of Engineering, Electronics and Analytics
ZEA-2 – Electronic Systems
Britta Hallmann
52425 Jülich
E-Mail: verwaltung.zea2@fz-juelich.de