15/04/2021
Science 4 Refugees

PhD Position - Conception, Design and Development of Neuromorphic Learning Systems with Supercomputer Support

This job offer has expired


  • ORGANISATION/COMPANY
    Forschungszentrum Jülich
  • RESEARCH FIELD
    All
  • RESEARCHER PROFILE
    First Stage Researcher (R1)
  • APPLICATION DEADLINE
    10/05/2021 00:00 - Europe/Brussels
  • LOCATION
    Germany › Aachen
  • TYPE OF CONTRACT
    To be defined
  • JOB STATUS
    Other

OFFER DESCRIPTION

Work group:

PGI-15 - Neuromorphic Software Eco System

Area of research:

PHD Thesis

Job description:

The newly created Neuromorphic Software Ecosystem Institute (PGI-15) strives to create novel computing technologies that learn and work like the brain, by combining the fundamental and the applied. Our long-term research goal is to emulate high-level, cognitive function in dedicated neuromorphic hardware systems. To achieve this, we study neural circuits and emerging devices as physical substrates that implement a class of machine learning algorithms and design hardware systems that efficiently implement these algorithms. Applications from our research include computer vision, brain-computer interfaces and scientific data analysis.Adaptive “life-long” learning during online task performance is an aspirational goal of AI technologies. Thanks to recent hardware and algorithmic advances, neuromorphic processors now have the capabilities for adaptive, on-line learning via specialized circuits and emerging memory devices. Their performance is now on par with the performance of small deep neural networks. However, learning in practical scenarios remains generally unsolved due to data inefficiency and catastrophic forgetting. Today, these challenges hinder the deployment of the on-chip learning capabilities of neuromorphic hardware.One solution to this problem is to pre-train networks off-line, and transfer them onto the neuromorphic hardware. This project will develop a learning framework that leverages the supercomputing facilities at FZ Jülich to support the pre-training of digital and/or mixed signal neuromorphic hardware available at PGI-15. The resulting approach will be demonstrated in a computer vision or signal processing task.

Your Job:

  • Develop multilayer spiking neural network training and inference algorithms within constraints of digital hardware and emerging memory devices.
  • Analysis of underlying gradient-based learning theory, the current state-of-the-art in neuromorphic computing hardware implementing SNNs and the mapping of spiking neural network learning and inference algorithms onto existing hardware.
  • Work with the Jülich Supercomputing Centre to run your algorithms/tools on large distributed computer systems, and accelerate/support the learning of neuromorphic hardware.
  • Write research articles, regularly participate in international conferences to present your own work, and learn about state-of-the-art neuromorphic engineering and their applications.

Your Profile:

  • Masters degree in physics, electrical/electronic engineering, computer science or related field
  • Previous experience on neural networks, machine learning and machine learning software frameworks
  • Strong mathematical and programming background, knowledge of modelling of non-linear dynamical systems is a plus
  • Excellent knowledge and experience in programming (e.g. Python, C, C++) and computer skills (e.g. Linux).
  • Experience with neuromorphic hardware or edge deep learning accelerators is a plus
  • Excellent ability for cooperative collaboration, Interdisciplinary and cross-topical thinking
  • Very good communication skills in English. German language skills are not necessary.
  • Team-minded, self-reliant, and highly motivated character

Our Offer:

We work on the very latest issues that impact our society and are offering you the chance to actively help in shaping the change! We offer ideal conditions for you to complete your doctoral degree:

  • A world-leading, interdisciplinary and international research environment, provided with state-of-the-art experimental equipment and versatile opportunities to grow as a young and curious researcher.
  • Flexible working hours and 30 days of annual leave
  • A large research campus with green spaces, offering the best possible means for networking with colleagues and pursuing sports alongside work
  • A structured doctoral degree programme for you and your supervisors with a comprehensive further training and networking package on our doctoral researchers’ platform JuDocs www.fz-juelich.de/judocs

  • Targeted services for international employees, e.g. through our International Advisory Service

The position is initially for a fixed term of 3 years, with possible long-term prospects. Pay in line with 75% of pay group 13 of the Collective Agreement for the Public Service (TVöD-Bund) and additionally 60 % of a monthly salary as special payment („Christmas bonus“). Further information on doctoral degrees at Forschungszentrum Jülich including our other locations is available at: www.fz-juelich.de/gp/Careers_DocsForschungszentrum Jülich promotes equal opportunities and diversity in its employment relations.We welcome applications from disabled persons.

This research center is part of the Helmholtz Association of German Research Centers. With more than 42,000 employees and an annual budget of over € 5 billion, the Helmholtz Association is Germany's largest scientific organisation.

Work location(s)
1 position(s) available at
Forschungszentrum Jülich
Germany
Aachen

EURAXESS offer ID: 630159
Posting organisation offer ID: 2021D-049

Disclaimer:

The responsibility for the jobs published on this website, including the job description, lies entirely with the publishing institutions. The application is handled uniquely by the employer, who is also fully responsible for the recruitment and selection processes.

 

Please contact support@euraxess.org if you wish to download all jobs in XML.