PhD Position in Systems and Control Theory for Energy-based Learning

RUG; Groningen; On-site; EUR 36,000 - 45,000; Full time

Benefits offered by this job

232 vacation hours per year

End-of-year bonus

Professional development

Teaching experience (10%)

Job summary

The University of Groningen invites applications for a PhD position in Systems and Control Theory for Energy-based Learning. You will develop a system-theoretic framework and energy-based learning algorithms for analog circuits, aiming at efficient, local learning rules within dissipative networks.

You will work on the ERC Starting Grant project and collaborate with an international team, contributing to teaching and supervision where appropriate.

Qualifications

• Master’s degree in Systems and Control, (Applied) Mathematics, Electrical Engineering, or closely related field.
• Strong mathematical background and ability to conduct theoretical research.
• Excellent English communication skills, written and spoken.
• Strong analytical abilities, creativity, persistence, and collaboration.
• Familiarity with circuit theory, networked systems, machine learning, or neuromorphic computing is an advantage.

Responsibilities

• Developing a system-theoretic framework that models learning as the feedback interconnection between continuous-time circuit dynamics and optimization algorithms.
• Designing novel energy-based learning algorithms for training analog circuits directly from input-output data.
• Developing fully decentralised learning rules that rely on local circuit information and are suitable for large-scale systems.
• Establishing rigorous theoretical guarantees for convergence and scalability of the proposed learning algorithms.
• Extending the theory from analog circuits to more general dissipative networks.
• Testing and validating the developed methods.
• Publishing research findings in leading international journals and conferences and presenting your work at scientific meetings.
• Contributing to teaching activities and supervising Bachelor’s and Master’s students where appropriate.

Skills

Strong mathematical background

Excellent English communication

Analytical abilities

Creativity

Persistence

Collaborative

Education

Master’s degree in Systems and Control

Master’s degree in Applied Mathematics

Master’s degree in Electrical Engineering

Job description

PhD position in Systems and Control Theory for Energy-based Learning

Are you excited about developing new mathematical foundations for energy-efficient computing? Do you want to contribute to cutting-edge research at the intersection of systems and control theory, optimization, circuit theory, and neuromorphic computing?

The University of Groningen is seeking a highly motivated PhD candidate to work on a fundamental research project on systems and control theory for learning in neuromorphic circuits. Neuromorphic computing is an analog, brain-inspired computing paradigm with the potential to drastically reduce energy consumption while enabling faster inference than conventional digital architectures. A major challenge, however, is the development and analysis of dedicated algorithms for training analog circuits directly from data.

In this PhD project, you will develop a novel system-theoretic framework for learning in analog circuits and dissipative networks. We will view learning as a feedback interconnection of continuous-time (circuit) dynamics and an optimization algorithm. The key idea is to develop algorithms that minimise cost functions inspired by notions of energy, leading to highly efficient, local learning rules.

PhD position in Systems and Control Theory for Energy-based Learning

As a PhD candidate, you will develop mathematical theory for learning in nonlinear and dynamic circuits. Building on preliminary results for resistive circuits, you will study circuits containing memristive and capacitive elements, as well as more general dissipative networks. The project combines systems and control theory, circuit theory, optimization, and machine learning, with the ultimate goal of advancing the mathematical foundations of physics-based learning.

Your responsibilities include:

• Developing a system-theoretic framework that models learning as the feedback interconnection between continuous-time circuit dynamics and optimization algorithms.
• Designing novel energy-based learning algorithms for training analog circuits directly from input-output data.
• Developing fully decentralised learning rules that rely on local circuit information and are suitable for large-scale systems.
• Establishing rigorous theoretical guarantees for convergence and scalability of the proposed learning algorithms.
• Extending the theory from analog circuits to more general dissipative networks.
• Testing and validating the developed methods.
• Publishing research findings in leading international journals and conferences and presenting your work at scientific meetings.
• Contributing to teaching activities and supervising Bachelor’s and Master’s students where appropriate.

Faculty of Science and Engineering

Who are you?

We are looking for an enthusiastic researcher who enjoys solving challenging problems and working in an international research environment.

You should have:

• A Master’s degree in Systems and Control, (Applied) Mathematics, Electrical Engineering, or a closely related field.
• A strong mathematical background and an interest in conducting theoretical research.
• Excellent English communication skills, both written and spoken.
• Strong analytical abilities, creativity, persistence, and the ability to collaborate effectively.
• Familiarity with circuit theory, networked systems, machine learning, or neuromorphic computing is considered an advantage, but is not required.

What can you expect from us?

• In accordance with the collective labor agreement for Dutch universities, we offer a salary of at least € 3.204up to a maximum of € 4.051 (promovendus)gross per month for a full-time employment contract.
• 232 vacation hours per year, based on a 38-hour workweek (1.0 FTE). You can also work more or fewer hours in exchange for more or fewer free hours. For example, with a 40-hour workweek, you save 96 extra free hours, and with a 36-hour workweek, you lose 96 hours.
• End-of-year bonus of 8.3% and 8% holiday allowance.
• Extensive opportunities for personal and professional development.
• A full-time position (1.0 FTE). The successful candidate will first be offered a temporary position of one year with the option of renewal for another three years. Prolongation of the contract is contingent on sufficient progress in the first year to indicate that a successful completion of the PhD thesis within the next three years is to be expected. A PhD training programme is part of the agreement and the successful candidate will be enrolled in the Graduate School of Science and Engineering.Teaching: employed PhD candidates are expected to spend 10% of their working hours on teaching.

Where will you be working?

At the University of Groningen (UG), researchers from all fields of academia and technology are working on academic challenges and societal questions. Lecturers prepare their students for meaningful careers within or outside the academic world. Interdisciplinary research and teaching, sharing of knowledge, collaboration with businesses, government institutions, and societal organizations are aspects that are of the utmost importance to this European top university. The UG aims to be an open academic community with an inclusive and safe working climate that invites you to add your value.

The successful candidate will join the Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence within the Faculty of Science and Engineering at the University of Groningen.

The research will be carried out in the Systems, Control and Optimization Group. Our group is part of the Jan C. Willems Center for Systems and Control that unites the different control groups in Groningen. This is a leading center (ranked first in the EU (fourth in Europe) according to the 2024 Shanghai Ranking). The successful candidate will benefit from connections within the center, as well as regular seminars, joint group meetings, and interaction with other PhD students and postdocs in a lively and supportive environment.

The PhD project is embedded within the European Research Council (ERC) Starting Grant project “Energy-based learning of complex dynamical systems” (E-BLOCS), led by Dr. Henk van Waarde. The PhD student will actively work together with the other members of the project, and also has many opportunities for international collaboration, research visits, and interdisciplinary training.

Do you have any questions or need more information?

Questions about your application process?

When scheduling meetings, we will take your schedule into account as much as possible.

The University of Groningen considers social safety important. We strive to be a university where staff and students feel respected and at home, regardless of differences in background, experiences, perspectives, and identity. For more information, see also our page about our diversity policy.

Our selection procedure follows the guidelines of the NVP Application Code.