PhD Student in ML Approaches for Wireless Communications Engineering

The Silicon Austria Labs – Doctoral College (SAL-DC) is a novel doctoral training programme for researchers focusing on the field of electronic based systems (EBS). SAL cooperates with industry, academic, and scientific partners on a regional, national, and international level with the aim to build an excellent research network and ecosystem for EBS. Fellows benefit from the training offered by SAL-DC in a highly international, interdisciplinary, and intersectoral setting to become future research leaders.

Your future responsibilities

We plan to inte­grate and combine deep learning methods into/​with conven­tional phys­ical models in order to improve nonlinear modeling for elec­tronic devices like e.g. commu­ni­ca­tions and radio frequency (RF) trans­ceivers. In partic­ular, we will enhance or replace conven­tional signal process­ing models like e.g. Volterra series, Wiener-models, Hammer­stein models or memory poly­no­mials with new tech­niques of machine learning. Involved re­search fields are deep learning, deep unfolding, model –based neural networks, few shot learning, meta learning (transfer models from one device to another), sequence analysis using LSTMs and trans­formers/​BERT. Rein­force­ment learning methods should be consid­ered for improving models that have delayed signals, there­fore also delayed error or reward signals. The goal is to enhance existing phys­ical models by new deep learning tech­niques to make model simu­la­tion faster without losing preci­sion and modeling capacity or to improve existing models using new machine learning approaches. Also online and tracking models should be inves­ti­gated, that is, models that adapt to the current envi­ron­ment like temper­a­ture, humidity, power consump­tion, voltage devi­a­tions, fast changing system para­me­ters etc. These online methods might be combined or substi­tuted by few shot and meta-learning methods. 
Further­more, we also plan to enhance and/​or substi­tute model-based signal process­ing blocks like e.g. pre-coding, digital pre-distor­tion, nonlinear distor­tion miti­ga­tion, or adap­tive channel esti­ma­tion/​equal­iza­tion, by machine learning approaches.

Your profile

Technical Skills:
  • Master’s degree (for PhD position) in computer science, mechatronics, electrical engineering, mathematics, physics, or similar subject
  • knowledge in one or more of the following application domains: signal processing, machine learning

Social Skills:
  • willingness and ability to work in a team
  • persistent researcher
  • well-structured and goal-oriented working style
  • reliability and excellent interpersonal skills
  • hands-on mentality

Personal Skills:
  • English level C1

Important Facts

  • Begin­ning of the employ­ment: September 2020
  • This posi­tion is endowed with a gross annual salary of € 40.978 based on the collec­tive agree­ment for re­search („Forschungs-Kollek­tiv­ver­trag“) and depen­ding on your expe­ri­ence and skills.

Become part of Silicon Austria Labs

The top research center for electronic based systems (EBS). Unfold the future, unfold yourself.
Your browser is out of date!

Update your browser to view this website correctly. Update my browser now